Publications: Yoshua Bengio
Download CSV for Yoshua Bengio
| Title | Year | Citations | Score |
|---|---|---|---|
|
Gradient-based learning applied to document recognition
Proceedings of the IEEE 86 (11), 2278-2324, 1998 View on Google Scholar ↗ |
1998 | 62466 | 100.0% |
|
Generative adversarial nets
Advances in neural information processing systems 27, 2014 View on Google Scholar ↗ |
2014 | 72413 | 100.0% |
|
Deep learning
nature 521 (7553), 436-444, 2015 View on Google Scholar ↗ |
2015 | 75414 | 100.0% |
|
Understanding the difficulty of training deep feedforward neural networks
Proceedings of the thirteenth international conference on artificial …, 2010 View on Google Scholar ↗ |
2010 | 23258 | 100.0% |
|
Deep sparse rectifier neural networks
Proceedings of the fourteenth international conference on artificial …, 2011 View on Google Scholar ↗ |
2011 | 11620 | 100.0% |
|
Neural machine translation by jointly learning to align and translate
arXiv preprint arXiv:1409.0473, 2014 View on Google Scholar ↗ |
2014 | 32988 | 100.0% |
|
Representation learning: A review and new perspectives
IEEE transactions on pattern analysis and machine intelligence 35 (8), 1798-1828, 2013 View on Google Scholar ↗ |
2013 | 15011 | 100.0% |
|
Deep learning
MIT press, 2016 View on Google Scholar ↗ |
2016 | 60268 | 100.0% |
|
Learning phrase representations using RNN encoder-decoder for statistical machine translation
arXiv preprint arXiv:1406.1078, 2014 View on Google Scholar ↗ |
2014 | 28038 | 100.0% |
|
Graph attention networks
stat 1050 (20), 10-48550, 2017 View on Google Scholar ↗ |
2017 | 18407 | 99.9% |
|
Learning deep architectures for AI
Foundations and trends® in Machine Learning 2 (1), 1-127, 2009 View on Google Scholar ↗ |
2009 | 12191 | 99.9% |
|
Learning long-term dependencies with gradient descent is difficult
IEEE transactions on neural networks 5 (2), 157-166, 1994 View on Google Scholar ↗ |
1994 | 11920 | 99.9% |
|
Show, attend and tell: Neural image caption generation with visual attention
International conference on machine learning, 2048-2057, 2015 View on Google Scholar ↗ |
2015 | 11863 | 99.9% |
|
Empirical evaluation of gated recurrent neural networks on sequence modeling
arXiv preprint arXiv:1412.3555, 2014 View on Google Scholar ↗ |
2014 | 15030 | 99.9% |
|
A Neural probabilistic language model
Journal of Machine Learning Research 3, 1137-1155, 2003 View on Google Scholar ↗ |
2003 | 10999 | 99.9% |
|
How transferable are features in deep neural networks?
Advances in neural information processing systems 27, 2014 View on Google Scholar ↗ |
2014 | 10022 | 99.9% |
|
Extracting and composing robust features with denoising autoencoders
Proceedings of the 25th international conference on Machine learning, 1096-1103, 2008 View on Google Scholar ↗ |
2008 | 8666 | 99.9% |
|
Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion.
Journal of machine learning research 11 (12), 2010 View on Google Scholar ↗ |
2010 | 8744 | 99.9% |
|
Algorithms for hyper-parameter optimization
Advances in neural information processing systems 24, 2011 View on Google Scholar ↗ |
2011 | 6189 | 99.9% |
|
On the properties of neural machine translation: Encoder-decoder approaches
arXiv preprint arXiv:1409.1259, 2014 View on Google Scholar ↗ |
2014 | 8230 | 99.9% |
|
Random search for hyper-parameter optimization.
Journal of machine learning research 13 (2), 2012 View on Google Scholar ↗ |
2012 | 11401 | 99.9% |
|
On the difficulty of training recurrent neural networks
International conference on machine learning, 1310-1318, 2013 View on Google Scholar ↗ |
2013 | 6896 | 99.9% |
|
Greedy layer-wise training of deep networks
Advances in neural information processing systems 19, 2006 View on Google Scholar ↗ |
2006 | 6953 | 99.9% |
|
Convolutional networks for images, speech, and time series
The handbook of brain theory and neural networks 3361 (10), 1995, 1995 View on Google Scholar ↗ |
1995 | 7567 | 99.9% |
|
Curriculum learning
Proceedings of the 26th annual international conference on machine learning …, 2009 View on Google Scholar ↗ |
2009 | 5716 | 99.8% |
|
Brain tumor segmentation with deep neural networks
Medical image analysis 35, 18-31, 2017 View on Google Scholar ↗ |
2017 | 3344 | 99.7% |
|
Benchmarking graph neural networks
Journal of Machine Learning Research 24 (43), 1-48, 2023 View on Google Scholar ↗ |
2023 | 812 | 99.7% |
|
Binaryconnect: Training deep neural networks with binary weights during propagations
Advances in neural information processing systems 28, 2015 View on Google Scholar ↗ |
2015 | 3460 | 99.7% |
|
Learning deep representations by mutual information estimation and maximization
arXiv preprint arXiv:1808.06670, 2018 View on Google Scholar ↗ |
2018 | 2634 | 99.7% |
|
Machine learning for combinatorial optimization: a methodological tour d’horizon
European Journal of Operational Research 290 (2), 405-421, 2021 View on Google Scholar ↗ |
2021 | 1259 | 99.7% |
|
Maxout networks
International conference on machine learning, 1319-1327, 2013 View on Google Scholar ↗ |
2013 | 3052 | 99.7% |
|
Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1
arXiv preprint arXiv:1602.02830, 2016 View on Google Scholar ↗ |
2016 | 3410 | 99.6% |
|
Why does unsupervised pre-training help deep learning?
Proceedings of the thirteenth international conference on artificial …, 2010 View on Google Scholar ↗ |
2010 | 3472 | 99.6% |
|
Tackling climate change with machine learning
ACM Computing Surveys (CSUR) 55 (2), 1-96, 2022 View on Google Scholar ↗ |
2022 | 825 | 99.6% |
|
Attention-based models for speech recognition
Advances in neural information processing systems 28, 2015 View on Google Scholar ↗ |
2015 | 3077 | 99.6% |
|
Estimating or propagating gradients through stochastic neurons for conditional computation
arXiv preprint arXiv:1308.3432, 2013 View on Google Scholar ↗ |
2013 | 2713 | 99.6% |
|
On the number of linear regions of deep neural networks
Advances in neural information processing systems 27, 2014 View on Google Scholar ↗ |
2014 | 2664 | 99.6% |
|
A structured self-attentive sentence embedding
arXiv preprint arXiv:1703.03130, 2017 View on Google Scholar ↗ |
2017 | 2530 | 99.6% |
|
Practical recommendations for gradient-based training of deep architectures
Neural Networks: Tricks of the Trade: Second Edition, 437-478, 2012 View on Google Scholar ↗ |
2012 | 2920 | 99.5% |
|
Interpolation consistency training for semi-supervised learning
Neural Networks 145, 90-106, 2022 View on Google Scholar ↗ |
2022 | 693 | 99.5% |
|
Quantized neural networks: Training neural networks with low precision weights and activations
journal of machine learning research 18 (187), 1-30, 2018 View on Google Scholar ↗ |
2018 | 2076 | 99.5% |
|
Word representations: a simple and general method for semi-supervised learning
Proceedings of the 48th annual meeting of the association for computational …, 2010 View on Google Scholar ↗ |
2010 | 2926 | 99.5% |
|
Deep graph infomax
arXiv preprint arXiv:1809.10341, 2018 View on Google Scholar ↗ |
2018 | 2074 | 99.5% |
|
Toward causal representation learning
Proceedings of the IEEE 109 (5), 612-634, 2021 View on Google Scholar ↗ |
2021 | 930 | 99.5% |
|
Binarized neural networks
Advances in neural information processing systems 29, 2016 View on Google Scholar ↗ |
2016 | 2378 | 99.5% |
|
Domain adaptation for large-scale sentiment classification: A deep learning approach
Proceedings of the 28th international conference on machine learning (ICML …, 2011 View on Google Scholar ↗ |
2011 | 2254 | 99.4% |
|
Building end-to-end dialogue systems using generative hierarchical neural network models
Proceedings of the AAAI conference on artificial intelligence 30 (1), 2016 View on Google Scholar ↗ |
2016 | 2008 | 99.4% |
|
The one hundred layers tiramisu: Fully convolutional densenets for semantic segmentation
Proceedings of the IEEE conference on computer vision and pattern …, 2017 View on Google Scholar ↗ |
2017 | 1943 | 99.4% |
|
Nice: Non-linear independent components estimation
arXiv preprint arXiv:1410.8516, 2014 View on Google Scholar ↗ |
2014 | 2080 | 99.4% |
|
Fitnets: Hints for thin deep nets
arXiv preprint arXiv:1412.6550, 2014 View on Google Scholar ↗ |
2014 | 2050 | 99.4% |
|
Deep learning
MIT press, 2017 View on Google Scholar ↗ |
2017 | 1869 | 99.4% |
|
Manifold mixup: Better representations by interpolating hidden states
International conference on machine learning, 6438-6447, 2019 View on Google Scholar ↗ |
2019 | 1147 | 99.3% |
|
Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv 2014
arXiv preprint arXiv:1406.1078, 2020 View on Google Scholar ↗ |
2020 | 1022 | 99.3% |
|
A closer look at memorization in deep networks
International conference on machine learning, 233-242, 2017 View on Google Scholar ↗ |
2017 | 1702 | 99.3% |
|
HotpotQA: A dataset for diverse, explainable multi-hop question answering
arXiv preprint arXiv:1809.09600, 2018 View on Google Scholar ↗ |
2018 | 1519 | 99.3% |
|
Challenges in representation learning: A report on three machine learning contests
Neural Information Processing: 20th International Conference, ICONIP 2013 …, 2013 View on Google Scholar ↗ |
2013 | 1846 | 99.3% |
|
Contractive auto-encoders: Explicit invariance during feature extraction
Proceedings of the 28th international conference on international conference …, 2011 View on Google Scholar ↗ |
2011 | 1934 | 99.2% |
|
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
Advances in neural information processing systems 27, 2014 View on Google Scholar ↗ |
2014 | 1697 | 99.2% |
|
Theano: a CPU and GPU math expression compiler
Proceedings of the Python for scientific computing conference (SciPy) 4 (3), 1-7, 2010 View on Google Scholar ↗ |
2010 | 2022 | 99.1% |
|
On the spectral bias of neural networks
International Conference on Machine Learning, 5301-5310, 2019 View on Google Scholar ↗ |
2019 | 976 | 99.1% |
|
Deep learning of representations for unsupervised and transfer learning
Proceedings of ICML workshop on unsupervised and transfer learning, 17-36, 2012 View on Google Scholar ↗ |
2012 | 1772 | 99.1% |
|
End-to-end attention-based large vocabulary speech recognition
2016 IEEE international conference on acoustics, speech and signal …, 2016 View on Google Scholar ↗ |
2016 | 1429 | 99.1% |
|
Gradient flow in recurrent nets: the difficulty of learning long-term dependencies
A field guide to dynamical recurrent neural networks. IEEE Press, 2001 View on Google Scholar ↗ |
2001 | 2569 | 99.1% |
|
Semi-supervised learning by entropy minimization
Advances in neural information processing systems 17, 2004 View on Google Scholar ↗ |
2004 | 2276 | 99.1% |
|
Theano: new features and speed improvements
arXiv preprint arXiv:1211.5590, 2012 View on Google Scholar ↗ |
2012 | 1689 | 99.1% |
|
Visualizing higher-layer features of a deep network
University of Montreal 1341 (3), 1, 2009 View on Google Scholar ↗ |
2009 | 1642 | 99.0% |
|
Mutual information neural estimation
International conference on machine learning, 531-540, 2018 View on Google Scholar ↗ |
2018 | 1185 | 99.0% |
|
Melgan: Generative adversarial networks for conditional waveform synthesis
Advances in neural information processing systems 32, 2019 View on Google Scholar ↗ |
2019 | 895 | 99.0% |
|
Scaling learning algorithms towards AI
Large-scale kernel machines 34 (5), 1-41, 2007 View on Google Scholar ↗ |
2007 | 1881 | 99.0% |
|
A recurrent latent variable model for sequential data
Advances in neural information processing systems 28, 2015 View on Google Scholar ↗ |
2015 | 1392 | 99.0% |
|
N-BEATS: Neural basis expansion analysis for interpretable time series forecasting
arXiv preprint arXiv:1905.10437, 2019 View on Google Scholar ↗ |
2019 | 872 | 99.0% |
|
A hierarchical latent variable encoder-decoder model for generating dialogues
Proceedings of the AAAI conference on artificial intelligence 31 (1), 2017 View on Google Scholar ↗ |
2017 | 1226 | 98.9% |
|
A deep learning framework for neuroscience
Nature neuroscience 22 (11), 1761-1770, 2019 View on Google Scholar ↗ |
2019 | 848 | 98.9% |
|
Deep learning for AI
Communications of the ACM 64 (7), 58-65, 2021 View on Google Scholar ↗ |
2021 | 507 | 98.9% |
|
An empirical investigation of catastrophic forgetting in gradient-based neural networks
arXiv preprint arXiv:1312.6211, 2013 View on Google Scholar ↗ |
2013 | 1343 | 98.9% |
|
How to construct deep recurrent neural networks
arXiv preprint arXiv:1312.6026, 2013 View on Google Scholar ↗ |
2013 | 1315 | 98.9% |
|
On using very large target vocabulary for neural machine translation
arXiv preprint arXiv:1412.2007, 2014 View on Google Scholar ↗ |
2014 | 1194 | 98.8% |
|
SpeechBrain: A general-purpose speech toolkit
arXiv preprint arXiv:2106.04624, 2021 View on Google Scholar ↗ |
2021 | 467 | 98.8% |
|
Exploring strategies for training deep neural networks.
Journal of machine learning research 10 (1), 2009 View on Google Scholar ↗ |
2009 | 1369 | 98.7% |
|
Gated feedback recurrent neural networks
International conference on machine learning, 2067-2075, 2015 View on Google Scholar ↗ |
2015 | 1049 | 98.7% |
|
Deep learning
nature 521 (7553), 436-444, 2015 View on Google Scholar ↗ |
2015 | 1043 | 98.6% |
|
Plug & play generative networks: Conditional iterative generation of images in latent space
Proceedings of the IEEE conference on computer vision and pattern …, 2017 View on Google Scholar ↗ |
2017 | 943 | 98.6% |
|
Gradient based sample selection for online continual learning
Advances in neural information processing systems 32, 2019 View on Google Scholar ↗ |
2019 | 667 | 98.5% |
|
Inductive biases for deep learning of higher-level cognition
Proceedings of the Royal Society A 478 (2266), 20210068, 2022 View on Google Scholar ↗ |
2022 | 261 | 98.5% |
|
An empirical evaluation of deep architectures on problems with many factors of variation
Proceedings of the 24th international conference on Machine learning, 473-480, 2007 View on Google Scholar ↗ |
2007 | 1373 | 98.5% |
|
Theano: A Python framework for fast computation of mathematical expressions
arXiv e-prints, arXiv: 1605.02688, 2016 View on Google Scholar ↗ |
2016 | 930 | 98.4% |
|
Hierarchical probabilistic neural network language model
International workshop on artificial intelligence and statistics, 246-252, 2005 View on Google Scholar ↗ |
2005 | 1362 | 98.4% |
|
Object recognition with gradient-based learning
Shape, contour and grouping in computer vision, 319-345, 1999 View on Google Scholar ↗ |
1999 | 1575 | 98.4% |
|
Speaker recognition from raw waveform with sincnet
2018 IEEE spoken language technology workshop (SLT), 1021-1028, 2018 View on Google Scholar ↗ |
2018 | 779 | 98.3% |
|
Advances in neural information processing systems
Curran Associates, Inc 27, 2672-2680, 2014 View on Google Scholar ↗ |
2014 | 870 | 98.2% |
|
Learning structured embeddings of knowledge bases
Proceedings of the AAAI conference on artificial intelligence 25 (1), 301-306, 2011 View on Google Scholar ↗ |
2011 | 1093 | 98.2% |
|
Unitary evolution recurrent neural networks
International conference on machine learning, 1120-1128, 2016 View on Google Scholar ↗ |
2016 | 823 | 98.2% |
|
A semantic matching energy function for learning with multi-relational data: Application to word-sense disambiguation
Machine Learning 94, 233-259, 2014 View on Google Scholar ↗ |
2014 | 832 | 98.1% |
|
Deep learning of representations: Looking forward
International conference on statistical language and speech processing, 1-37, 2013 View on Google Scholar ↗ |
2013 | 880 | 98.1% |
|
Out-of-sample extensions for lle, isomap, mds, eigenmaps, and spectral clustering
Advances in neural information processing systems 16, 2003 View on Google Scholar ↗ |
2003 | 1397 | 98.0% |
|
Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription
arXiv preprint arXiv:1206.6392, 2012 View on Google Scholar ↗ |
2012 | 919 | 98.0% |
|
Scientific discovery in the age of artificial intelligence
Nature 620 (7972), 47-60, 2023 View on Google Scholar ↗ |
2023 | 153 | 98.0% |
|
No unbiased estimator of the variance of k-fold cross-validation
Advances in Neural Information Processing Systems 16, 2003 View on Google Scholar ↗ |
2003 | 1336 | 97.9% |
|
Using recurrent neural networks for slot filling in spoken language understanding
IEEE/ACM Transactions on Audio, Speech, and Language Processing 23 (3), 530-539, 2014 View on Google Scholar ↗ |
2014 | 739 | 97.8% |
|
Classification using discriminative restricted Boltzmann machines
Proceedings of the 25th international conference on Machine learning, 536-543, 2008 View on Google Scholar ↗ |
2008 | 1015 | 97.8% |
|
Representational power of restricted Boltzmann machines and deep belief networks
Neural computation 20 (6), 1631-1649, 2008 View on Google Scholar ↗ |
2008 | 1013 | 97.8% |
|
Sharp minima can generalize for deep nets
International Conference on Machine Learning, 1019-1028, 2017 View on Google Scholar ↗ |
2017 | 673 | 97.8% |
|
Inference for the generalization error
Advances in neural information processing systems 12, 1999 View on Google Scholar ↗ |
1999 | 1241 | 97.8% |
|
Mine: mutual information neural estimation
arXiv preprint arXiv:1801.04062, 2018 View on Google Scholar ↗ |
2018 | 617 | 97.7% |
|
Neural machine translation by jointly learning to align and translate. arXiv 2014
arXiv preprint arXiv:1409.0473, 2014 View on Google Scholar ↗ |
2014 | 711 | 97.7% |
|
Multi-way, multilingual neural machine translation with a shared attention mechanism
arXiv preprint arXiv:1601.01073, 2016 View on Google Scholar ↗ |
2016 | 675 | 97.7% |
|
Understanding intermediate layers using linear classifier probes
arXiv preprint arXiv:1610.01644, 2016 View on Google Scholar ↗ |
2016 | 671 | 97.6% |
|
Mode regularized generative adversarial networks
arXiv preprint arXiv:1612.02136, 2016 View on Google Scholar ↗ |
2016 | 670 | 97.6% |
|
An actor-critic algorithm for sequence prediction
arXiv preprint arXiv:1607.07086, 2016 View on Google Scholar ↗ |
2016 | 667 | 97.6% |
|
Professor forcing: A new algorithm for training recurrent networks
Advances in neural information processing systems 29, 2016 View on Google Scholar ↗ |
2016 | 666 | 97.6% |
|
Pointing the unknown words
arXiv preprint arXiv:1603.08148, 2016 View on Google Scholar ↗ |
2016 | 662 | 97.6% |
|
SampleRNN: An unconditional end-to-end neural audio generation model
arXiv preprint arXiv:1612.07837, 2016 View on Google Scholar ↗ |
2016 | 654 | 97.6% |
|
Training deep neural networks with low precision multiplications
arXiv preprint arXiv:1412.7024, 2014 View on Google Scholar ↗ |
2014 | 679 | 97.5% |
|
Understanding the exploding gradient problem
CoRR, abs/1211.5063 2 (417), 1, 2012 View on Google Scholar ↗ |
2012 | 750 | 97.4% |
|
Metagan: An adversarial approach to few-shot learning
Advances in neural information processing systems 31, 2018 View on Google Scholar ↗ |
2018 | 557 | 97.4% |
|
Hierarchical multiscale recurrent neural networks
arXiv preprint arXiv:1609.01704, 2016 View on Google Scholar ↗ |
2016 | 620 | 97.4% |
|
Generalized denoising auto-encoders as generative models
Advances in neural information processing systems 26, 2013 View on Google Scholar ↗ |
2013 | 692 | 97.4% |
|
Advances in optimizing recurrent networks
2013 IEEE international conference on acoustics, speech and signal …, 2013 View on Google Scholar ↗ |
2013 | 687 | 97.3% |
|
Theano: A CPU and GPU math compiler in Python
Proc. 9th python in science conf 1, 3-10, 2010 View on Google Scholar ↗ |
2010 | 837 | 97.3% |
|
On using monolingual corpora in neural machine translation
arXiv preprint arXiv:1503.03535, 2015 View on Google Scholar ↗ |
2015 | 613 | 97.3% |
|
What regularized auto-encoders learn from the data-generating distribution
The Journal of Machine Learning Research 15 (1), 3563-3593, 2014 View on Google Scholar ↗ |
2014 | 629 | 97.3% |
|
Experience grounds language
arXiv preprint arXiv:2004.10151, 2020 View on Google Scholar ↗ |
2020 | 343 | 97.3% |
|
Equilibrated adaptive learning rates for non-convex optimization
Advances in neural information processing systems 28, 2015 View on Google Scholar ↗ |
2015 | 603 | 97.2% |
|
An empirical study of example forgetting during deep neural network learning
arXiv preprint arXiv:1812.05159, 2018 View on Google Scholar ↗ |
2018 | 511 | 97.2% |
|
A hierarchical recurrent encoder-decoder for generative context-aware query suggestion
proceedings of the 24th ACM international on conference on information and …, 2015 View on Google Scholar ↗ |
2015 | 582 | 97.1% |
|
Generalization in deep learning
arXiv preprint arXiv:1710.05468 1 (8), 2017 View on Google Scholar ↗ |
2017 | 538 | 97.1% |
|
Unsupervised feature learning and deep learning: A review and new perspectives
CoRR, abs/1206.5538 1 (2665), 2012, 2012 View on Google Scholar ↗ |
2012 | 672 | 97.0% |
|
End-to-end continuous speech recognition using attention-based recurrent nn: First results
arXiv preprint arXiv:1412.1602, 2014 View on Google Scholar ↗ |
2014 | 574 | 96.9% |
|
Toward trustworthy AI development: mechanisms for supporting verifiable claims
arXiv preprint arXiv:2004.07213, 2020 View on Google Scholar ↗ |
2020 | 306 | 96.8% |
|
Char2wav: End-to-end speech synthesis
View on Google Scholar ↗ |
2017 | 489 | 96.8% |
|
Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding.
Interspeech, 3771-3775, 2013 View on Google Scholar ↗ |
2013 | 590 | 96.7% |
|
Gradient starvation: A learning proclivity in neural networks
Advances in Neural Information Processing Systems 34, 1256-1272, 2021 View on Google Scholar ↗ |
2021 | 211 | 96.7% |
|
Gflownet foundations
Journal of Machine Learning Research 24 (210), 1-55, 2023 View on Google Scholar ↗ |
2023 | 95 | 96.6% |
|
Bayesian model-agnostic meta-learning
Advances in neural information processing systems 31, 2018 View on Google Scholar ↗ |
2018 | 443 | 96.6% |
|
Describing multimedia content using attention-based encoder-decoder networks
IEEE Transactions on Multimedia 17 (11), 1875-1886, 2015 View on Google Scholar ↗ |
2015 | 511 | 96.6% |
|
Emonets: Multimodal deep learning approaches for emotion recognition in video
Journal on Multimodal User Interfaces 10, 99-111, 2016 View on Google Scholar ↗ |
2016 | 481 | 96.5% |
|
A meta-transfer objective for learning to disentangle causal mechanisms
arXiv preprint arXiv:1901.10912, 2019 View on Google Scholar ↗ |
2019 | 339 | 96.5% |
|
Towards end-to-end speech recognition with deep convolutional neural networks
arXiv preprint arXiv:1701.02720, 2017 View on Google Scholar ↗ |
2017 | 463 | 96.5% |
|
Three factors influencing minima in sgd
arXiv preprint arXiv:1711.04623, 2017 View on Google Scholar ↗ |
2017 | 451 | 96.4% |
|
Convergence properties of the k-means algorithms
Advances in neural information processing systems 7, 1994 View on Google Scholar ↗ |
1994 | 756 | 96.4% |
|
Equilibrium propagation: Bridging the gap between energy-based models and backpropagation
Frontiers in computational neuroscience 11, 24, 2017 View on Google Scholar ↗ |
2017 | 444 | 96.3% |
|
Multi-task self-supervised learning for robust speech recognition
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 View on Google Scholar ↗ |
2020 | 276 | 96.3% |
|
The difficulty of training deep architectures and the effect of unsupervised pre-training
Artificial intelligence and statistics, 153-160, 2009 View on Google Scholar ↗ |
2009 | 628 | 96.1% |
|
Gmnn: Graph markov neural networks
International conference on machine learning, 5241-5250, 2019 View on Google Scholar ↗ |
2019 | 306 | 96.1% |
|
Speech model pre-training for end-to-end spoken language understanding
arXiv preprint arXiv:1904.03670, 2019 View on Google Scholar ↗ |
2019 | 304 | 96.0% |
|
Learning general purpose distributed sentence representations via large scale multi-task learning
arXiv preprint arXiv:1804.00079, 2018 View on Google Scholar ↗ |
2018 | 386 | 96.0% |
|
Recurrent independent mechanisms
arXiv preprint arXiv:1909.10893, 2019 View on Google Scholar ↗ |
2019 | 298 | 95.9% |
|
Deep generative stochastic networks trainable by backprop
International Conference on Machine Learning, 226-234, 2014 View on Google Scholar ↗ |
2014 | 465 | 95.9% |
|
Towards an automatic turing test: Learning to evaluate dialogue responses
arXiv preprint arXiv:1708.07149, 2017 View on Google Scholar ↗ |
2017 | 400 | 95.8% |
|
Light gated recurrent units for speech recognition
IEEE Transactions on Emerging Topics in Computational Intelligence 2 (2), 92-102, 2018 View on Google Scholar ↗ |
2018 | 372 | 95.8% |
|
Graph neural networks with learnable structural and positional representations
arXiv preprint arXiv:2110.07875, 2021 View on Google Scholar ↗ |
2021 | 173 | 95.7% |
|
Image-to-image translation for cross-domain disentanglement
Advances in neural information processing systems 31, 2018 View on Google Scholar ↗ |
2018 | 366 | 95.7% |
|
Predicting covid-19 pneumonia severity on chest x-ray with deep learning
Cureus 12 (7), 2020 View on Google Scholar ↗ |
2020 | 241 | 95.7% |
|
Bilbowa: Fast bilingual distributed representations without word alignments
International Conference on Machine Learning, 748-756, 2015 View on Google Scholar ↗ |
2015 | 430 | 95.7% |
|
Zero-data learning of new tasks.
AAAI 1 (2), 3, 2008 View on Google Scholar ↗ |
2008 | 616 | 95.7% |
|
3rd International Conference on Learning Representations
ICLR, San Diego, 2015 View on Google Scholar ↗ |
2015 | 423 | 95.6% |
|
Revisiting fundamentals of experience replay
International Conference on Machine Learning, 3061-3071, 2020 View on Google Scholar ↗ |
2020 | 233 | 95.5% |
|
Neural networks with few multiplications
arXiv preprint arXiv:1510.03009, 2015 View on Google Scholar ↗ |
2015 | 415 | 95.5% |
|
A character-level decoder without explicit segmentation for neural machine translation
arXiv preprint arXiv:1603.06147, 2016 View on Google Scholar ↗ |
2016 | 390 | 95.5% |
|
Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv
arXiv preprint arXiv:1412.3555 10, 2014 View on Google Scholar ↗ |
2014 | 431 | 95.5% |
|
Towards biologically plausible deep learning
arXiv preprint arXiv:1502.04156, 2015 View on Google Scholar ↗ |
2015 | 414 | 95.5% |
|
Catalyzing next-generation artificial intelligence through neuroai
Nature communications 14 (1), 1597, 2023 View on Google Scholar ↗ |
2023 | 74 | 95.5% |
|
Hyena hierarchy: Towards larger convolutional language models
arXiv preprint arXiv:2302.10866, 2023 View on Google Scholar ↗ |
2023 | 74 | 95.5% |
|
Invariance principle meets information bottleneck for out-of-distribution generalization
Advances in Neural Information Processing Systems 34, 3438-3450, 2021 View on Google Scholar ↗ |
2021 | 164 | 95.5% |
|
Joint learning of words and meaning representations for open-text semantic parsing
Artificial intelligence and statistics, 127-135, 2012 View on Google Scholar ↗ |
2012 | 481 | 95.4% |
|
Drawing and recognizing chinese characters with recurrent neural network
IEEE transactions on pattern analysis and machine intelligence 40 (4), 849-862, 2017 View on Google Scholar ↗ |
2017 | 366 | 95.4% |
|
Zoneout: Regularizing rnns by randomly preserving hidden activations
arXiv preprint arXiv:1606.01305, 2016 View on Google Scholar ↗ |
2016 | 378 | 95.3% |
|
Flow network based generative models for non-iterative diverse candidate generation
Advances in Neural Information Processing Systems 34, 27381-27394, 2021 View on Google Scholar ↗ |
2021 | 156 | 95.2% |
|
Learning problem-agnostic speech representations from multiple self-supervised tasks
arXiv preprint arXiv:1904.03416, 2019 View on Google Scholar ↗ |
2019 | 255 | 95.1% |
|
The pytorch-kaldi speech recognition toolkit
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 View on Google Scholar ↗ |
2019 | 254 | 95.1% |
|
Unsupervised state representation learning in atari
Advances in neural information processing systems 32, 2019 View on Google Scholar ↗ |
2019 | 253 | 95.0% |
|
A deep reinforcement learning chatbot
arXiv preprint arXiv:1709.02349, 2017 View on Google Scholar ↗ |
2017 | 339 | 95.0% |
|
Better mixing via deep representations
International conference on machine learning, 552-560, 2013 View on Google Scholar ↗ |
2013 | 420 | 95.0% |
|
Combining modality specific deep neural networks for emotion recognition in video
Proceedings of the 15th ACM on International conference on multimodal …, 2013 View on Google Scholar ↗ |
2013 | 416 | 94.9% |
|
Difference target propagation
Machine Learning and Knowledge Discovery in Databases: European Conference …, 2015 View on Google Scholar ↗ |
2015 | 372 | 94.9% |
|
Graphmix: Improved training of gnns for semi-supervised learning
Proceedings of the AAAI conference on artificial intelligence 35 (11), 10024 …, 2021 View on Google Scholar ↗ |
2021 | 146 | 94.7% |
|
Reseg: A recurrent neural network-based model for semantic segmentation
Proceedings of the IEEE conference on computer vision and pattern …, 2016 View on Google Scholar ↗ |
2016 | 337 | 94.7% |
|
Generating factoid questions with recurrent neural networks: The 30m factoid question-answer corpus
arXiv preprint arXiv:1603.06807, 2016 View on Google Scholar ↗ |
2016 | 335 | 94.7% |
|
Dendritic cortical microcircuits approximate the backpropagation algorithm
Advances in neural information processing systems 31, 2018 View on Google Scholar ↗ |
2018 | 302 | 94.7% |
|
Noisy activation functions
International conference on machine learning, 3059-3068, 2016 View on Google Scholar ↗ |
2016 | 334 | 94.6% |
|
Revisiting natural gradient for deep networks
arXiv preprint arXiv:1301.3584, 2013 View on Google Scholar ↗ |
2013 | 393 | 94.5% |
|
Deep learning. 2016
MIT press, 2016 View on Google Scholar ↗ |
2016 | 329 | 94.5% |
|
Shallow vs. deep sum-product networks
Advances in neural information processing systems 24, 2011 View on Google Scholar ↗ |
2011 | 453 | 94.5% |
|
Online and offline handwritten Chinese character recognition: A comprehensive study and new benchmark
Pattern Recognition 61, 348-360, 2017 View on Google Scholar ↗ |
2017 | 309 | 94.4% |
|
Hierarchical recurrent neural networks for long-term dependencies
Advances in neural information processing systems 8, 1995 View on Google Scholar ↗ |
1995 | 508 | 94.3% |
|
On the expressive power of deep architectures
International conference on algorithmic learning theory, 18-36, 2011 View on Google Scholar ↗ |
2011 | 437 | 94.3% |
|
Learning algorithms for the classification restricted Boltzmann machine
The Journal of Machine Learning Research 13 (1), 643-669, 2012 View on Google Scholar ↗ |
2012 | 400 | 94.2% |
|
Batch normalized recurrent neural networks
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016 View on Google Scholar ↗ |
2016 | 314 | 94.2% |
|
Gradient-based optimization of hyperparameters
Neural computation 12 (8), 1889-1900, 2000 View on Google Scholar ↗ |
2000 | 625 | 94.2% |
|
Maximum-likelihood augmented discrete generative adversarial networks
arXiv preprint arXiv:1702.07983, 2017 View on Google Scholar ↗ |
2017 | 298 | 94.2% |
|
Renet: A recurrent neural network based alternative to convolutional networks
arXiv preprint arXiv:1505.00393, 2015 View on Google Scholar ↗ |
2015 | 335 | 94.2% |
|
Graph attention networks. arXiv 2017
arXiv preprint arXiv:1710.10903, 2017 View on Google Scholar ↗ |
2017 | 296 | 94.1% |
|
An input output HMM architecture
Advances in neural information processing systems 7, 1994 View on Google Scholar ↗ |
1994 | 518 | 94.1% |
|
Pylearn2: a machine learning research library
arXiv preprint arXiv:1308.4214, 2013 View on Google Scholar ↗ |
2013 | 365 | 94.0% |
|
Managing diversity in regression ensembles.
Journal of machine learning research 6 (9), 2005 View on Google Scholar ↗ |
2005 | 484 | 93.7% |
|
Learning normalized inputs for iterative estimation in medical image segmentation
Medical image analysis 44, 1-13, 2018 View on Google Scholar ↗ |
2018 | 257 | 93.6% |
|
Learning a synaptic learning rule
Université de Montréal, Département d'informatique et de recherche …, 1990 View on Google Scholar ↗ |
1990 | 424 | 93.5% |
|
Model evaluation for extreme risks
arXiv preprint arXiv:2305.15324, 2023 View on Google Scholar ↗ |
2023 | 52 | 93.5% |
|
On the optimization of a synaptic learning rule
Preprints Conf. Optimality in Artificial and Biological Neural Networks 2, 2013 View on Google Scholar ↗ |
2013 | 339 | 93.4% |
|
Learning deep physiological models of affect
IEEE Computational intelligence magazine 8 (2), 20-33, 2013 View on Google Scholar ↗ |
2013 | 339 | 93.4% |
|
On the number of response regions of deep feed forward networks with piece-wise linear activations
arXiv preprint arXiv:1312.6098, 2013 View on Google Scholar ↗ |
2013 | 338 | 93.4% |
|
A parallel mixture of SVMs for very large scale problems
Advances in Neural Information Processing Systems 14, 2001 View on Google Scholar ↗ |
2001 | 539 | 93.3% |
|
Towards end-to-end spoken language understanding
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018 View on Google Scholar ↗ |
2018 | 245 | 93.3% |
|
Incorporating second-order functional knowledge for better option pricing
Advances in neural information processing systems 13, 2000 View on Google Scholar ↗ |
2000 | 540 | 93.2% |
|
Deep learning (Vol. 1)
MIT press Massachusetts, USA, 2017 View on Google Scholar ↗ |
2017 | 259 | 93.2% |
|
The consciousness prior
arXiv preprint arXiv:1709.08568, 2017 View on Google Scholar ↗ |
2017 | 258 | 93.1% |
|
Measuring the tendency of cnns to learn surface statistical regularities
arXiv preprint arXiv:1711.11561, 2017 View on Google Scholar ↗ |
2017 | 257 | 93.1% |
|
Input-output HMMs for sequence processing
IEEE Transactions on Neural Networks 7 (5), 1231-1249, 1996 View on Google Scholar ↗ |
1996 | 444 | 93.0% |
|
The handbook of brain theory and neural networks
MIT press, 1998 View on Google Scholar ↗ |
1998 | 468 | 92.9% |
|
Hemis: Hetero-modal image segmentation
Medical Image Computing and Computer-Assisted Intervention–MICCAI 2016: 19th …, 2016 View on Google Scholar ↗ |
2016 | 261 | 92.9% |
|
Bayesian structure learning with generative flow networks
Uncertainty in Artificial Intelligence, 518-528, 2022 View on Google Scholar ↗ |
2022 | 72 | 92.8% |
|
Theano: Deep learning on gpus with python
NIPS 2011, BigLearning Workshop, Granada, Spain 3 (0), 2011 View on Google Scholar ↗ |
2011 | 354 | 92.7% |
|
Multiresolution recurrent neural networks: An application to dialogue response generation
Proceedings of the AAAI Conference on Artificial Intelligence 31 (1), 2017 View on Google Scholar ↗ |
2017 | 241 | 92.6% |
|
The need for privacy with public digital contact tracing during the COVID-19 pandemic
The Lancet Digital Health 2 (7), e342-e344, 2020 View on Google Scholar ↗ |
2020 | 151 | 92.5% |
|
The manifold tangent classifier
Advances in neural information processing systems 24, 2011 View on Google Scholar ↗ |
2011 | 344 | 92.5% |
|
Biological sequence design with gflownets
International Conference on Machine Learning, 9786-9801, 2022 View on Google Scholar ↗ |
2022 | 69 | 92.4% |
|
Low precision arithmetic for deep learning.
ICLR (Workshop), 2015 View on Google Scholar ↗ |
2015 | 262 | 92.2% |
|
11 label propagation and quadratic criterion
located at: https://www. researchgate. net/profile/Y_Bengio/publication …, 2006 View on Google Scholar ↗ |
2006 | 388 | 92.0% |
|
The problem of learning long-term dependencies in recurrent networks
IEEE international conference on neural networks, 1183-1188, 1993 View on Google Scholar ↗ |
1993 | 360 | 92.0% |
|
Markovian models for sequential data
Neural computing surveys 2 (199), 129-162, 1999 View on Google Scholar ↗ |
1999 | 441 | 91.9% |
|
Interventional causal representation learning
International conference on machine learning, 372-407, 2023 View on Google Scholar ↗ |
2023 | 42 | 91.8% |
|
Global optimization of a neural network-hidden Markov model hybrid
IEEE transactions on Neural Networks 3 (2), 252-259, 1992 View on Google Scholar ↗ |
1992 | 365 | 91.8% |
|
BabyAI: First steps towards grounded language learning with a human in the loop
International Conference on Learning Representations 105, 2019 View on Google Scholar ↗ |
2019 | 164 | 91.8% |
|
Improving and generalizing flow-based generative models with minibatch optimal transport
arXiv preprint arXiv:2302.00482, 2023 View on Google Scholar ↗ |
2023 | 41 | 91.7% |
|
Proceedings of the thirteenth international conference on artificial intelligence and statistics
Understanding the difficulty of training deep feedforward neural networks …, 2010 View on Google Scholar ↗ |
2010 | 335 | 91.5% |
|
Deep learning book
MIT Press 521 (7553), 800, 2016 View on Google Scholar ↗ |
2016 | 225 | 91.5% |
|
Rnnlogic: Learning logic rules for reasoning on knowledge graphs
arXiv preprint arXiv:2010.04029, 2020 View on Google Scholar ↗ |
2020 | 134 | 91.4% |
|
Trajectory balance: Improved credit assignment in gflownets
Advances in Neural Information Processing Systems 35, 5955-5967, 2022 View on Google Scholar ↗ |
2022 | 62 | 91.4% |
|
Denoising criterion for variational auto-encoding framework
Proceedings of the AAAI conference on artificial intelligence 31 (1), 2017 View on Google Scholar ↗ |
2017 | 208 | 91.3% |
|
Boundary-seeking generative adversarial networks
arXiv preprint arXiv:1702.08431, 2017 View on Google Scholar ↗ |
2017 | 207 | 91.3% |
|
Infobot: Transfer and exploration via the information bottleneck
arXiv preprint arXiv:1901.10902, 2019 View on Google Scholar ↗ |
2019 | 155 | 91.2% |
|
Kernel matching pursuit
Machine learning 48, 165-187, 2002 View on Google Scholar ↗ |
2002 | 411 | 91.2% |
|
Learning neural causal models from unknown interventions
arXiv preprint arXiv:1910.01075, 2019 View on Google Scholar ↗ |
2019 | 154 | 91.2% |
|
Learning neural generative dynamics for molecular conformation generation
arXiv preprint arXiv:2102.10240, 2021 View on Google Scholar ↗ |
2021 | 93 | 91.1% |
|
High quality document image compression with" DjVu"
Journal of Electronic Imaging 7 (3), 410-425, 1998 View on Google Scholar ↗ |
1998 | 381 | 91.1% |
|
Unsupervised and transfer learning challenge: a deep learning approach
Proceedings of ICML Workshop on Unsupervised and Transfer Learning, 97-110, 2012 View on Google Scholar ↗ |
2012 | 279 | 91.1% |
|
Z-forcing: Training stochastic recurrent networks
Advances in neural information processing systems 30, 2017 View on Google Scholar ↗ |
2017 | 202 | 91.0% |
|
Artificial neural networks applied to taxi destination prediction
arXiv preprint arXiv:1508.00021, 2015 View on Google Scholar ↗ |
2015 | 229 | 90.9% |
|
Figureqa: An annotated figure dataset for visual reasoning
arXiv preprint arXiv:1710.07300, 2017 View on Google Scholar ↗ |
2017 | 198 | 90.8% |
|
Advances in neural information processing systems
(No Title) 19, 153, 2007 View on Google Scholar ↗ |
2007 | 334 | 90.8% |
|
Boosting neural networks
Neural computation 12 (8), 1869-1887, 2000 View on Google Scholar ↗ |
2000 | 408 | 90.6% |
|
Fine-grained attention mechanism for neural machine translation
Neurocomputing 284, 171-176, 2018 View on Google Scholar ↗ |
2018 | 181 | 90.6% |
|
Learning to understand phrases by embedding the dictionary
Transactions of the Association for Computational Linguistics 4, 17-30, 2016 View on Google Scholar ↗ |
2016 | 205 | 90.6% |
|
Audio Chord Recognition with Recurrent Neural Networks.
ISMIR, 335-340, 2013 View on Google Scholar ↗ |
2013 | 252 | 90.6% |
|
Theano: A Python framework for fast computation of mathematical expressions
arXiv preprint arXiv:1605.02688, 2016 View on Google Scholar ↗ |
2016 | 203 | 90.5% |
|
Parameterizing branch-and-bound search trees to learn branching policies
Proceedings of the aaai conference on artificial intelligence 35 (5), 3931-3939, 2021 View on Google Scholar ↗ |
2021 | 86 | 90.3% |
|
Disentangling factors of variation for facial expression recognition
Computer Vision–ECCV 2012: 12th European Conference on Computer Vision …, 2012 View on Google Scholar ↗ |
2012 | 259 | 90.3% |
|
BigBrain 3D atlas of cortical layers: Cortical and laminar thickness gradients diverge in sensory and motor cortices
PLoS biology 18 (4), e3000678, 2020 View on Google Scholar ↗ |
2020 | 119 | 90.3% |
|
Higher order contractive auto-encoder
Machine Learning and Knowledge Discovery in Databases: European Conference …, 2011 View on Google Scholar ↗ |
2011 | 275 | 90.2% |
|
Coordination among neural modules through a shared global workspace
arXiv preprint arXiv:2103.01197, 2021 View on Google Scholar ↗ |
2021 | 85 | 90.2% |
|
Hierarchical neural network generative models for movie dialogues
arXiv preprint arXiv:1507.04808 7 (8), 434-441, 2015 View on Google Scholar ↗ |
2015 | 215 | 90.2% |
|
Babyai: A platform to study the sample efficiency of grounded language learning
arXiv preprint arXiv:1810.08272, 2018 View on Google Scholar ↗ |
2018 | 173 | 90.1% |
|
Learning eigenfunctions links spectral embedding and kernel PCA
Neural computation 16 (10), 2197-2219, 2004 View on Google Scholar ↗ |
2004 | 348 | 90.1% |
|
Object-centric image generation from layouts
Proceedings of the AAAI Conference on Artificial Intelligence 35 (3), 2647-2655, 2021 View on Google Scholar ↗ |
2021 | 84 | 90.1% |
|
Do neural dialog systems use the conversation history effectively? an empirical study
arXiv preprint arXiv:1906.01603, 2019 View on Google Scholar ↗ |
2019 | 138 | 90.0% |
|
Justifying and generalizing contrastive divergence
Neural computation 21 (6), 1601-1621, 2009 View on Google Scholar ↗ |
2009 | 287 | 89.9% |
|
Knowledge matters: Importance of prior information for optimization
The Journal of Machine Learning Research 17 (1), 226-257, 2016 View on Google Scholar ↗ |
2016 | 191 | 89.8% |
|
Gated orthogonal recurrent units: On learning to forget
Neural computation 31 (4), 765-783, 2019 View on Google Scholar ↗ |
2019 | 135 | 89.8% |
|
Variance reduction in sgd by distributed importance sampling
arXiv preprint arXiv:1511.06481, 2015 View on Google Scholar ↗ |
2015 | 207 | 89.7% |
|
Hybrid models for learning to branch
Advances in neural information processing systems 33, 18087-18097, 2020 View on Google Scholar ↗ |
2020 | 112 | 89.6% |
|
Causalworld: A robotic manipulation benchmark for causal structure and transfer learning
arXiv preprint arXiv:2010.04296, 2020 View on Google Scholar ↗ |
2020 | 112 | 89.6% |
|
Architectural complexity measures of recurrent neural networks
Advances in neural information processing systems 29, 2016 View on Google Scholar ↗ |
2016 | 187 | 89.6% |
|
Blocks and fuel: Frameworks for deep learning
arXiv preprint arXiv:1506.00619, 2015 View on Google Scholar ↗ |
2015 | 204 | 89.6% |
|
Learning to navigate the synthetically accessible chemical space using reinforcement learning
International conference on machine learning, 3668-3679, 2020 View on Google Scholar ↗ |
2020 | 111 | 89.5% |
|
Deep learning for NLP (without magic)
Tutorial Abstracts of ACL 2012, 5-5, 2012 View on Google Scholar ↗ |
2012 | 242 | 89.5% |
|
Adaptive importance sampling to accelerate training of a neural probabilistic language model
IEEE Transactions on Neural Networks 19 (4), 713-722, 2008 View on Google Scholar ↗ |
2008 | 282 | 89.3% |
|
Improving generative adversarial networks with denoising feature matching
International conference on learning representations, 2016 View on Google Scholar ↗ |
2016 | 183 | 89.3% |
|
Generative flow networks for discrete probabilistic modeling
International Conference on Machine Learning, 26412-26428, 2022 View on Google Scholar ↗ |
2022 | 51 | 89.3% |
|
Neural production systems
Advances in Neural Information Processing Systems 34, 25673-25687, 2021 View on Google Scholar ↗ |
2021 | 78 | 89.1% |
|
Hyenadna: Long-range genomic sequence modeling at single nucleotide resolution
arXiv preprint arXiv:2306.15794, 2023 View on Google Scholar ↗ |
2023 | 32 | 89.1% |
|
Count-ception: Counting by fully convolutional redundant counting
Proceedings of the IEEE International conference on computer vision …, 2017 View on Google Scholar ↗ |
2017 | 167 | 88.9% |
|
On multiplicative integration with recurrent neural networks
Advances in neural information processing systems 29, 2016 View on Google Scholar ↗ |
2016 | 176 | 88.8% |
|
Your gan is secretly an energy-based model and you should use discriminator driven latent sampling
Advances in Neural Information Processing Systems 33, 12275-12287, 2020 View on Google Scholar ↗ |
2020 | 102 | 88.5% |
|
Meta-learning framework with applications to zero-shot time-series forecasting
Proceedings of the AAAI Conference on Artificial Intelligence 35 (10), 9242-9250, 2021 View on Google Scholar ↗ |
2021 | 74 | 88.5% |
|
Bayesian model-agnostic meta-learning
arXiv preprint arXiv:1806.03836, 2018 View on Google Scholar ↗ |
2018 | 148 | 88.4% |
|
A theory of continuous generative flow networks
International Conference on Machine Learning, 18269-18300, 2023 View on Google Scholar ↗ |
2023 | 30 | 88.4% |
|
Learned-norm pooling for deep feedforward and recurrent neural networks
Machine Learning and Knowledge Discovery in Databases: European Conference …, 2014 View on Google Scholar ↗ |
2014 | 194 | 88.3% |
|
Quaternion recurrent neural networks
arXiv preprint arXiv:1806.04418, 2018 View on Google Scholar ↗ |
2018 | 146 | 88.2% |
|
The curse of highly variable functions for local kernel machines
Advances in neural information processing systems 18, 2005 View on Google Scholar ↗ |
2005 | 280 | 88.0% |
|
Montreal neural machine translation systems for WMT’15
Proceedings of the tenth workshop on statistical machine translation, 134-140, 2015 View on Google Scholar ↗ |
2015 | 179 | 87.9% |
|
Toward next-generation artificial intelligence: Catalyzing the neuroai revolution
arXiv preprint arXiv:2210.08340, 2022 View on Google Scholar ↗ |
2022 | 45 | 87.8% |
|
Multi-prediction deep Boltzmann machines
Advances in Neural Information Processing Systems 26, 2013 View on Google Scholar ↗ |
2013 | 198 | 87.6% |
|
Consciousness in artificial intelligence: insights from the science of consciousness
arXiv preprint arXiv:2308.08708, 2023 View on Google Scholar ↗ |
2023 | 28 | 87.6% |
|
Reweighted wake-sleep
arXiv preprint arXiv:1406.2751, 2014 View on Google Scholar ↗ |
2014 | 182 | 87.6% |
|
The causal-neural connection: Expressiveness, learnability, and inference
Advances in Neural Information Processing Systems 34, 10823-10836, 2021 View on Google Scholar ↗ |
2021 | 69 | 87.5% |
|
Maximum entropy generators for energy-based models
arXiv preprint arXiv:1901.08508, 2019 View on Google Scholar ↗ |
2019 | 112 | 87.5% |
|
GJ n
Hinton," Deep learning 521 (7553), 436-444, 2015 View on Google Scholar ↗ |
2015 | 173 | 87.5% |
|
Highres-net: Recursive fusion for multi-frame super-resolution of satellite imagery
arXiv preprint arXiv:2002.06460, 2020 View on Google Scholar ↗ |
2020 | 94 | 87.3% |
|
Deep directed generative models with energy-based probability estimation
arXiv preprint arXiv:1606.03439, 2016 View on Google Scholar ↗ |
2016 | 156 | 87.3% |
|
LeRec: A NN/HMM hybrid for on-line handwriting recognition
Neural computation 7 (6), 1289-1303, 1995 View on Google Scholar ↗ |
1995 | 242 | 87.2% |
|
Predicting tactical solutions to operational planning problems under imperfect information
INFORMS Journal on Computing 34 (1), 227-242, 2022 View on Google Scholar ↗ |
2022 | 43 | 87.2% |
|
Topmoumoute online natural gradient algorithm
Advances in neural information processing systems 20, 2007 View on Google Scholar ↗ |
2007 | 244 | 87.0% |
|
6.2. 2.3 softmax units for multinoulli output distributions
Deep learning 180, 2016 View on Google Scholar ↗ |
2016 | 151 | 86.8% |
|
Systematic generalisation with group invariant predictions
International Conference on Learning Representations, 2020 View on Google Scholar ↗ |
2020 | 90 | 86.7% |
|
Deup: Direct epistemic uncertainty prediction
arXiv preprint arXiv:2102.08501, 2021 View on Google Scholar ↗ |
2021 | 65 | 86.7% |
|
Marginalized denoising auto-encoders for nonlinear representations
International conference on machine learning, 1476-1484, 2014 View on Google Scholar ↗ |
2014 | 171 | 86.7% |
|
How auto-encoders could provide credit assignment in deep networks via target propagation
arXiv preprint arXiv:1407.7906, 2014 View on Google Scholar ↗ |
2014 | 170 | 86.6% |
|
Convex neural networks
Advances in neural information processing systems 18, 2005 View on Google Scholar ↗ |
2005 | 253 | 86.6% |
|
A neural knowledge language model
arXiv preprint arXiv:1608.00318, 2016 View on Google Scholar ↗ |
2016 | 148 | 86.5% |
|
Combined reinforcement learning via abstract representations
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 3582-3589, 2019 View on Google Scholar ↗ |
2019 | 104 | 86.5% |
|
Hyperbolic discounting and learning over multiple horizons
arXiv preprint arXiv:1902.06865, 2019 View on Google Scholar ↗ |
2019 | 103 | 86.4% |
|
An end-to-end framework for molecular conformation generation via bilevel programming
International Conference on Machine Learning, 11537-11547, 2021 View on Google Scholar ↗ |
2021 | 63 | 86.3% |
|
Neural networks for speech and sequence recognition
(No Title), 1996 View on Google Scholar ↗ |
1996 | 237 | 86.3% |
|
K-local hyperplane and convex distance nearest neighbor algorithms
Advances in neural information processing systems 14, 2001 View on Google Scholar ↗ |
2001 | 270 | 86.2% |
|
Convolutional networks
Deep learning 2016, 330-372, 2016 View on Google Scholar ↗ |
2016 | 144 | 86.1% |
|
a Courville, A
Deep learning 1 (2), 2016 View on Google Scholar ↗ |
2016 | 144 | 86.1% |
|
Generative adversarial nets
Advances in neural information processing systems 27, 2672-2680, 2014 View on Google Scholar ↗ |
2014 | 165 | 86.1% |
|
Multi-objective gflownets
International conference on machine learning, 14631-14653, 2023 View on Google Scholar ↗ |
2023 | 25 | 86.1% |
|
Learning GFlowNets from partial episodes for improved convergence and stability
International Conference on Machine Learning, 23467-23483, 2023 View on Google Scholar ↗ |
2023 | 25 | 86.1% |
|
Deep learners benefit more from out-of-distribution examples
Proceedings of the Fourteenth International Conference on Artificial …, 2011 View on Google Scholar ↗ |
2011 | 195 | 85.8% |
|
Deep learning for patient-specific kidney graft survival analysis
arXiv preprint arXiv:1705.10245, 2017 View on Google Scholar ↗ |
2017 | 132 | 85.8% |
|
Scaling equilibrium propagation to deep convnets by drastically reducing its gradient estimator bias
Frontiers in neuroscience 15, 633674, 2021 View on Google Scholar ↗ |
2021 | 61 | 85.8% |
|
Wasserstein dependency measure for representation learning
Advances in Neural Information Processing Systems 32, 2019 View on Google Scholar ↗ |
2019 | 99 | 85.8% |
|
Interpretable convolutional filters with sincnet
arXiv preprint arXiv:1811.09725, 2018 View on Google Scholar ↗ |
2018 | 121 | 85.8% |
|
Efficient non-parametric function induction in semi-supervised learning
International Workshop on Artificial Intelligence and Statistics, 96-103, 2005 View on Google Scholar ↗ |
2005 | 236 | 85.7% |
|
Deep belief networks are compact universal approximators
Neural computation 22 (8), 2192-2207, 2010 View on Google Scholar ↗ |
2010 | 208 | 85.6% |
|
Deep verifier networks: Verification of deep discriminative models with deep generative models
Proceedings of the AAAI Conference on Artificial Intelligence 35 (8), 7002-7010, 2021 View on Google Scholar ↗ |
2021 | 60 | 85.5% |
|
Neural models for key phrase detection and question generation
arXiv preprint arXiv:1706.04560, 2017 View on Google Scholar ↗ |
2017 | 128 | 85.4% |
|
Weakly supervised representation learning with sparse perturbations
Advances in Neural Information Processing Systems 35, 15516-15528, 2022 View on Google Scholar ↗ |
2022 | 38 | 85.3% |
|
Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks
MIT Press 3361 (10), 1995, 1995 View on Google Scholar ↗ |
1995 | 207 | 85.2% |
|
Residual connections encourage iterative inference
arXiv preprint arXiv:1710.04773, 2017 View on Google Scholar ↗ |
2017 | 126 | 85.1% |
|
Deep learning. Book in preparation for MIT Press
URL¡ http://www. deeplearningbook. org 1, 2016 View on Google Scholar ↗ |
2016 | 135 | 85.1% |
|
Deconstructing the ladder network architecture
International conference on machine learning, 2368-2376, 2016 View on Google Scholar ↗ |
2016 | 134 | 85.0% |
|
End-to-end online writer identification with recurrent neural network
IEEE transactions on human-machine systems 47 (2), 285-292, 2016 View on Google Scholar ↗ |
2016 | 134 | 85.0% |
|
Learning fixed points in generative adversarial networks: From image-to-image translation to disease detection and localization
Proceedings of the IEEE/CVF international conference on computer vision, 191-200, 2019 View on Google Scholar ↗ |
2019 | 94 | 85.0% |
|
Interpolated adversarial training: Achieving robust neural networks without sacrificing too much accuracy
Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security …, 2019 View on Google Scholar ↗ |
2019 | 92 | 84.7% |
|
Context-dependent word representation for neural machine translation
Computer Speech & Language 45, 149-160, 2017 View on Google Scholar ↗ |
2017 | 122 | 84.6% |
|
Toward training recurrent neural networks for lifelong learning
Neural computation 32 (1), 1-35, 2020 View on Google Scholar ↗ |
2020 | 78 | 84.6% |
|
On integrating a language model into neural machine translation
Computer Speech & Language 45, 137-148, 2017 View on Google Scholar ↗ |
2017 | 119 | 84.2% |
|
Ensemble of generative and discriminative techniques for sentiment analysis of movie reviews
arXiv preprint arXiv:1412.5335, 2014 View on Google Scholar ↗ |
2014 | 146 | 84.2% |
|
A walk with sgd
arXiv preprint arXiv:1802.08770, 2018 View on Google Scholar ↗ |
2018 | 108 | 84.1% |
|
On the relation between the sharpest directions of DNN loss and the SGD step length
arXiv preprint arXiv:1807.05031, 2018 View on Google Scholar ↗ |
2018 | 108 | 84.1% |
|
Hnhn: Hypergraph networks with hyperedge neurons
arXiv preprint arXiv:2006.12278, 2020 View on Google Scholar ↗ |
2020 | 75 | 84.0% |
|
Graph attention networks
arXiv preprint arXiv:1710.10903, 2017 View on Google Scholar ↗ |
2017 | 117 | 84.0% |
|
Use machine learning to find energy materials
Nature 552 (7683), 23-27, 2017 View on Google Scholar ↗ |
2017 | 117 | 84.0% |
|
Obamanet: Photo-realistic lip-sync from text
arXiv preprint arXiv:1801.01442, 2017 View on Google Scholar ↗ |
2017 | 117 | 84.0% |
|
Globally trained handwritten word recognizer using spatial representation, convolutional neural networks, and hidden Markov models
Advances in neural information processing systems 6, 1993 View on Google Scholar ↗ |
1993 | 176 | 83.7% |
|
Iterative alternating neural attention for machine reading
arXiv preprint arXiv:1606.02245, 2016 View on Google Scholar ↗ |
2016 | 124 | 83.7% |
|
From system 1 deep learning to system 2 deep learning
Neural Information Processing Systems, 2019 View on Google Scholar ↗ |
2019 | 86 | 83.6% |
|
Convolutional neural networks for mesh-based parcellation of the cerebral cortex
Medical Imaging with Deep Learning, 2022 View on Google Scholar ↗ |
2022 | 34 | 83.6% |
|
Training end-to-end analog neural networks with equilibrium propagation
arXiv preprint arXiv:2006.01981, 2020 View on Google Scholar ↗ |
2020 | 73 | 83.6% |
|
Better training of gflownets with local credit and incomplete trajectories
arXiv preprint arXiv:2302.01687, 2023 View on Google Scholar ↗ |
2023 | 21 | 83.6% |
|
Neural networks: Tricks of the trade
Practical Recommendations for Gradient-Based Training of Deep Architectures …, 2012 View on Google Scholar ↗ |
2012 | 159 | 83.6% |
|
Inherent privacy limitations of decentralized contact tracing apps
Journal of the American Medical Informatics Association 28 (1), 193-195, 2021 View on Google Scholar ↗ |
2021 | 53 | 83.5% |
|
Chatpainter: Improving text to image generation using dialogue
arXiv preprint arXiv:1802.08216, 2018 View on Google Scholar ↗ |
2018 | 104 | 83.5% |
|
Quaternion convolutional neural networks for end-to-end automatic speech recognition
arXiv preprint arXiv:1806.07789, 2018 View on Google Scholar ↗ |
2018 | 103 | 83.4% |
|
STDP-compatible approximation of backpropagation in an energy-based model
Neural computation 29 (3), 555-577, 2017 View on Google Scholar ↗ |
2017 | 111 | 83.1% |
|
Fitnets: Hints for thin deep nets
Proc. ICLR 2, 3, 2015 View on Google Scholar ↗ |
2015 | 129 | 82.9% |
|
Neural net language models
Scholarpedia 3 (1), 3881, 2008 View on Google Scholar ↗ |
2008 | 180 | 82.9% |
|
Quick training of probabilistic neural nets by importance sampling
International Workshop on Artificial Intelligence and Statistics, 17-24, 2003 View on Google Scholar ↗ |
2003 | 213 | 82.9% |
|
Equivariance with learned canonicalization functions
International Conference on Machine Learning, 15546-15566, 2023 View on Google Scholar ↗ |
2023 | 20 | 82.8% |
|
Modeling high-dimensional discrete data with multi-layer neural networks
Advances in Neural Information Processing Systems 12, 1999 View on Google Scholar ↗ |
1999 | 203 | 82.6% |
|
Sparse attentive backtracking: Temporal credit assignment through reminding
Advances in neural information processing systems 31, 2018 View on Google Scholar ↗ |
2018 | 98 | 82.5% |
|
Deep convolutional networks for quality assessment of protein folds
Bioinformatics 34 (23), 4046-4053, 2018 View on Google Scholar ↗ |
2018 | 98 | 82.5% |
|
An empirical analysis of dropout in piecewise linear networks
arXiv preprint arXiv:1312.6197, 2013 View on Google Scholar ↗ |
2013 | 140 | 82.3% |
|
A Very Fast Learning Method for Neural Networks Based on Sensitivity Analysis.
Journal of Machine Learning Research 7 (7), 2006 View on Google Scholar ↗ |
2006 | 179 | 82.0% |
|
GFlowNets for AI-driven scientific discovery
Digital Discovery 2 (3), 557-577, 2023 View on Google Scholar ↗ |
2023 | 19 | 82.0% |
|
Deep learning
Nature 29 (7553), 1-73, 2016 View on Google Scholar ↗ |
2016 | 111 | 81.8% |
|
Chunked autoregressive GAN for conditional waveform synthesis
arXiv preprint arXiv:2110.10139, 2021 View on Google Scholar ↗ |
2021 | 48 | 81.8% |
|
Learning to combine top-down and bottom-up signals in recurrent neural networks with attention over modules
International Conference on Machine Learning, 6972-6986, 2020 View on Google Scholar ↗ |
2020 | 65 | 81.6% |
|
Temporal Pooling and Multiscale Learning for Automatic Annotation and Ranking of Music Audio.
ISMIR, 729-734, 2011 View on Google Scholar ↗ |
2011 | 150 | 81.5% |
|
CACHE (Critical Assessment of Computational Hit-finding Experiments): A public–private partnership benchmarking initiative to enable the development of computational methods for hit-finding
Nature Reviews Chemistry 6 (4), 287-295, 2022 View on Google Scholar ↗ |
2022 | 30 | 81.5% |
|
GFlowNets and variational inference
arXiv preprint arXiv:2210.00580, 2022 View on Google Scholar ↗ |
2022 | 30 | 81.5% |
|
Multi-way, multilingual neural machine translation
Computer Speech & Language 45, 236-252, 2017 View on Google Scholar ↗ |
2017 | 101 | 81.4% |
|
Deep learning
Nature 521 (7553), 436-444, 2015 View on Google Scholar ↗ |
2015 | 117 | 81.3% |
|
GFlowNet-EM for learning compositional latent variable models
International Conference on Machine Learning, 13528-13549, 2023 View on Google Scholar ↗ |
2023 | 18 | 81.1% |
|
Regularization for deep learning
Deep learning, 216-261, 2016 View on Google Scholar ↗ |
2016 | 106 | 81.0% |
|
Deep feedforward networks
Deep learning, 2016 View on Google Scholar ↗ |
2016 | 106 | 81.0% |
|
Feature-wise transformations
Distill 3 (7), e11, 2018 View on Google Scholar ↗ |
2018 | 89 | 80.8% |
|
Learning independent features with adversarial nets for non-linear ica
arXiv preprint arXiv:1710.05050, 2017 View on Google Scholar ↗ |
2017 | 97 | 80.7% |
|
Straight to the tree: Constituency parsing with neural syntactic distance
arXiv preprint arXiv:1806.04168, 2018 View on Google Scholar ↗ |
2018 | 88 | 80.6% |
|
Modeling term dependencies with quantum language models for ir
Proceedings of the 36th international ACM SIGIR conference on Research and …, 2013 View on Google Scholar ↗ |
2013 | 127 | 80.6% |
|
Diva: Diverse visual feature aggregation for deep metric learning
Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23 …, 2020 View on Google Scholar ↗ |
2020 | 61 | 80.4% |
|
Proceedings of the 27th International Conference on Neural Information Processing Systems
Proceedings of the 27th International Conference on Neural Information …, 2014 View on Google Scholar ↗ |
2014 | 118 | 80.4% |
|
Hierarchical memory networks
arXiv preprint arXiv:1605.07427, 2016 View on Google Scholar ↗ |
2016 | 102 | 80.2% |
|
How does hemispheric specialization contribute to human-defining cognition?
Neuron 109 (13), 2075-2090, 2021 View on Google Scholar ↗ |
2021 | 44 | 80.2% |
|
Flow: A dataset and benchmark for floating waste detection in inland waters
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 View on Google Scholar ↗ |
2021 | 44 | 80.2% |
|
Learning speaker representations with mutual information
arXiv preprint arXiv:1812.00271, 2018 View on Google Scholar ↗ |
2018 | 86 | 80.2% |
|
Learning to compute word embeddings on the fly
arXiv preprint arXiv:1706.00286, 2017 View on Google Scholar ↗ |
2017 | 94 | 80.1% |
|
Small-gan: Speeding up gan training using core-sets
International Conference on Machine Learning, 9005-9015, 2020 View on Google Scholar ↗ |
2020 | 60 | 80.1% |
|
Tempered Markov chain Monte Carlo for training of restricted Boltzmann machines
Proceedings of the thirteenth international conference on artificial …, 2010 View on Google Scholar ↗ |
2010 | 149 | 80.1% |
|
Discrete-valued neural communication
Advances in Neural Information Processing Systems 34, 2109-2121, 2021 View on Google Scholar ↗ |
2021 | 43 | 79.7% |
|
Variational temporal abstraction
Advances in Neural Information Processing Systems 32, 2019 View on Google Scholar ↗ |
2019 | 69 | 79.7% |
|
Understanding representations learned in deep architectures
Technical Report 1355, Université de Montréal/DIRO, 2010 View on Google Scholar ↗ |
2010 | 145 | 79.6% |
|
A spike and slab restricted Boltzmann machine
Proceedings of the fourteenth international conference on artificial …, 2011 View on Google Scholar ↗ |
2011 | 134 | 79.5% |
|
On the saddle point problem for non-convex optimization
arXiv preprint arXiv:1405.4604, 2014 View on Google Scholar ↗ |
2014 | 112 | 79.4% |
|
Manifold parzen windows
Advances in neural information processing systems 15, 2002 View on Google Scholar ↗ |
2002 | 171 | 79.2% |
|
Towards non-saturating recurrent units for modelling long-term dependencies
Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 3280-3287, 2019 View on Google Scholar ↗ |
2019 | 67 | 79.1% |
|
Proceedings of the 21st International Conference on Neural Information Processing Systems
Curran Associates Inc., 2008 View on Google Scholar ↗ |
2008 | 143 | 78.9% |
|
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Association for Computational Linguistics. https://doi. org/10.3115/v1/d14-1179, 2014 View on Google Scholar ↗ |
2014 | 109 | 78.8% |
|
Problems in the deployment of machine-learned models in health care
CMAJ 193 (35), E1391-E1394, 2021 View on Google Scholar ↗ |
2021 | 41 | 78.8% |
|
Data-driven approach to encoding and decoding 3-d crystal structures
arXiv preprint arXiv:1909.00949, 2019 View on Google Scholar ↗ |
2019 | 66 | 78.8% |
|
On the interplay between noise and curvature and its effect on optimization and generalization
International Conference on Artificial Intelligence and Statistics, 3503-3513, 2020 View on Google Scholar ↗ |
2020 | 55 | 78.4% |
|
Deep learning needs a prefrontal cortex
Work Bridging AI Cogn Sci 107 (603-616), 1, 2020 View on Google Scholar ↗ |
2020 | 55 | 78.4% |
|
Proceedings of the fourteenth international conference on artificial intelligence and statistics
PMLR 15, 315-323, 2011 View on Google Scholar ↗ |
2011 | 126 | 78.3% |
|
Tell, draw, and repeat: Generating and modifying images based on continual linguistic instruction
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2019 View on Google Scholar ↗ |
2019 | 64 | 78.2% |
|
Managing ai risks in an era of rapid progress
arXiv preprint arXiv:2310.17688, 2023 View on Google Scholar ↗ |
2023 | 15 | 78.0% |
|
Non-normal recurrent neural network (nnrnn): learning long time dependencies while improving expressivity with transient dynamics
Advances in neural information processing systems 32, 2019 View on Google Scholar ↗ |
2019 | 63 | 77.8% |
|
Global training of document processing systems using graph transformer networks
proceedings of IEEE computer society conference on computer vision and …, 1997 View on Google Scholar ↗ |
1997 | 141 | 77.7% |
|
Learning anonymized representations with adversarial neural networks
arXiv preprint arXiv:1802.09386, 2018 View on Google Scholar ↗ |
2018 | 75 | 77.6% |
|
Evolving culture versus local minima
Growing adaptive machines: Combining development and learning in artificial …, 2014 View on Google Scholar ↗ |
2014 | 102 | 77.5% |
|
Disentangling factors of variation via generative entangling
arXiv preprint arXiv:1210.5474, 2012 View on Google Scholar ↗ |
2012 | 115 | 77.4% |
|
Large-scale feature learning with spike-and-slab sparse coding
arXiv preprint arXiv:1206.6407, 2012 View on Google Scholar ↗ |
2012 | 115 | 77.4% |
|
Model selection for small sample regression
Machine Learning 48, 9-23, 2002 View on Google Scholar ↗ |
2002 | 155 | 77.4% |
|
Beyond skill rating: Advanced matchmaking in ghost recon online
IEEE Transactions on Computational Intelligence and AI in Games 4 (3), 167-177, 2012 View on Google Scholar ↗ |
2012 | 114 | 77.2% |
|
Is a modular architecture enough?
Advances in Neural Information Processing Systems 35, 28747-28760, 2022 View on Google Scholar ↗ |
2022 | 24 | 77.2% |
|
On adversarial mixup resynthesis
Advances in neural information processing systems 32, 2019 View on Google Scholar ↗ |
2019 | 61 | 77.2% |
|
Multi-task learning for stock selection
Advances in neural information processing systems 9, 1996 View on Google Scholar ↗ |
1996 | 128 | 76.7% |
|
Reading checks with multilayer graph transformer networks
1997 IEEE International Conference on Acoustics, Speech, and Signal …, 1997 View on Google Scholar ↗ |
1997 | 133 | 76.6% |
|
Recurrent neural networks with limited numerical precision
arXiv preprint arXiv:1608.06902, 2016 View on Google Scholar ↗ |
2016 | 85 | 76.5% |
|
Covi white paper
arXiv preprint arXiv:2005.08502, 2020 View on Google Scholar ↗ |
2020 | 50 | 76.4% |
|
Rethinking distributional matching based domain adaptation
arXiv preprint arXiv:2006.13352, 2020 View on Google Scholar ↗ |
2020 | 50 | 76.4% |
|
Multi-image super-resolution for remote sensing using deep recurrent networks
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020 View on Google Scholar ↗ |
2020 | 50 | 76.4% |
|
Depth with nonlinearity creates no bad local minima in ResNets
Neural Networks 118, 167-174, 2019 View on Google Scholar ↗ |
2019 | 59 | 76.4% |
|
Combining modular skills in multitask learning
arXiv preprint arXiv:2202.13914, 2022 View on Google Scholar ↗ |
2022 | 23 | 76.4% |
|
A new era: Intelligent tutoring systems will transform online learning for millions
arXiv preprint arXiv:2203.03724, 2022 View on Google Scholar ↗ |
2022 | 23 | 76.4% |
|
Courville. a (2016) deep learning
Massachusetts Institute of Technology, 2017 View on Google Scholar ↗ |
2017 | 78 | 76.3% |
|
Overcoming the curse of sentence length for neural machine translation using automatic segmentation
arXiv preprint arXiv:1409.1257, 2014 View on Google Scholar ↗ |
2014 | 96 | 76.2% |
|
Fast and slow learning of recurrent independent mechanisms
arXiv preprint arXiv:2105.08710, 2021 View on Google Scholar ↗ |
2021 | 36 | 76.1% |
|
Attention based pruning for shift networks
2020 25th International Conference on Pattern Recognition (ICPR), 4054-4061, 2021 View on Google Scholar ↗ |
2021 | 36 | 76.1% |
|
Big neural networks waste capacity
arXiv preprint arXiv:1301.3583, 2013 View on Google Scholar ↗ |
2013 | 101 | 76.0% |
|
Object files and schemata: Factorizing declarative and procedural knowledge in dynamical systems
arXiv preprint arXiv:2006.16225, 2020 View on Google Scholar ↗ |
2020 | 49 | 76.0% |
|
A hybrid Pareto model for asymmetric fat-tailed data: the univariate case
Extremes 12, 53-76, 2009 View on Google Scholar ↗ |
2009 | 120 | 75.9% |
|
Taking on the curse of dimensionality in joint distributions using neural networks
IEEE Transactions on Neural Networks 11 (3), 550-557, 2000 View on Google Scholar ↗ |
2000 | 144 | 75.8% |
|
Collaborative filtering on a family of biological targets
Journal of chemical information and modeling 46 (2), 626-635, 2006 View on Google Scholar ↗ |
2006 | 128 | 75.7% |
|
Diet networks: thin parameters for fat genomics
arXiv preprint arXiv:1611.09340, 2016 View on Google Scholar ↗ |
2016 | 82 | 75.7% |
|
Representation mixing for TTS synthesis
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 View on Google Scholar ↗ |
2019 | 57 | 75.6% |
|
Recall traces: Backtracking models for efficient reinforcement learning
arXiv preprint arXiv:1804.00379, 2018 View on Google Scholar ↗ |
2018 | 68 | 75.6% |
|
FER-2013 face database
Universit de Montral 3, 2013 View on Google Scholar ↗ |
2013 | 99 | 75.6% |
|
A connectionist approach to speech recognition
International journal of pattern recognition and artificial intelligence 7 …, 1993 View on Google Scholar ↗ |
1993 | 107 | 75.4% |
|
Recurrent neural networks for missing or asynchronous data
Advances in neural information processing systems 8, 1995 View on Google Scholar ↗ |
1995 | 114 | 75.3% |
|
Discrete key-value bottleneck
International Conference on Machine Learning, 34431-34455, 2023 View on Google Scholar ↗ |
2023 | 13 | 75.2% |
|
Invariant representations for noisy speech recognition
arXiv preprint arXiv:1612.01928, 2016 View on Google Scholar ↗ |
2016 | 79 | 74.9% |
|
Dynamic layer normalization for adaptive neural acoustic modeling in speech recognition
arXiv preprint arXiv:1707.06065, 2017 View on Google Scholar ↗ |
2017 | 73 | 74.9% |
|
Decision trees do not generalize to new variations
Computational Intelligence 26 (4), 449-467, 2010 View on Google Scholar ↗ |
2010 | 113 | 74.7% |
|
Adversarial domain adaptation for stable brain-machine interfaces
arXiv preprint arXiv:1810.00045, 2018 View on Google Scholar ↗ |
2018 | 65 | 74.7% |
|
A generative process for sampling contractive auto-encoders
arXiv preprint arXiv:1206.6434, 2012 View on Google Scholar ↗ |
2012 | 101 | 74.7% |
|
Parallel tempering for training of restricted Boltzmann machines
Proceedings of the thirteenth international conference on artificial …, 2010 View on Google Scholar ↗ |
2010 | 112 | 74.5% |
|
Non-local manifold tangent learning
Advances in Neural Information Processing Systems 17, 2004 View on Google Scholar ↗ |
2004 | 129 | 74.5% |
|
Memory augmented neural networks with wormhole connections
arXiv preprint arXiv:1701.08718, 2017 View on Google Scholar ↗ |
2017 | 72 | 74.5% |
|
Manifold mixup: Encouraging meaningful on-manifold interpolation as a regularizer
arXiv preprint arXiv:1806.05236 7, 2018 View on Google Scholar ↗ |
2018 | 64 | 74.4% |
|
Deep learning cambridge
MS: MITPress, 2016 View on Google Scholar ↗ |
2016 | 77 | 74.3% |
|
Generative adversarial nets
Advances in neural information processing systems 2, 2672-2680, 2014 View on Google Scholar ↗ |
2014 | 88 | 74.2% |
|
Learning neural causal models with active interventions
arXiv preprint arXiv:2109.02429, 2021 View on Google Scholar ↗ |
2021 | 33 | 74.1% |
|
Disentangling the independently controllable factors of variation by interacting with the world
arXiv preprint arXiv:1802.09484, 2018 View on Google Scholar ↗ |
2018 | 63 | 74.1% |
|
Defactor: Differentiable edge factorization-based probabilistic graph generation
arXiv preprint arXiv:1811.09766, 2018 View on Google Scholar ↗ |
2018 | 63 | 74.1% |
|
Estimating or propagating gradients through stochastic neurons
arXiv preprint arXiv:1305.2982, 2013 View on Google Scholar ↗ |
2013 | 91 | 73.7% |
|
Autoencoders
Deep learning 1, 493-515, 2016 View on Google Scholar ↗ |
2016 | 75 | 73.7% |
|
GSNs: generative stochastic networks
Information and Inference: A Journal of the IMA 5 (2), 210-249, 2016 View on Google Scholar ↗ |
2016 | 75 | 73.7% |
|
Deep learning [http://www. deeplearningbook. org]
MIT Press, Cambridge, MA, 2016 View on Google Scholar ↗ |
2016 | 75 | 73.7% |
|
Word-level training of a handwritten word recognizer based on convolutional neural networks
Proceedings of the 12th IAPR International Conference on Pattern Recognition …, 1994 View on Google Scholar ↗ |
1994 | 104 | 73.7% |
|
Synergies between disentanglement and sparsity: Generalization and identifiability in multi-task learning
International Conference on Machine Learning, 18171-18206, 2023 View on Google Scholar ↗ |
2023 | 12 | 73.6% |
|
Combining Parameter-efficient Modules for Task-level Generalisation
Proceedings of the 17th Conference of the European Chapter of the …, 2023 View on Google Scholar ↗ |
2023 | 12 | 73.6% |
|
The curse of dimensionality for local kernel machines
Techn. Rep 1258 (12), 1, 2005 View on Google Scholar ↗ |
2005 | 117 | 73.5% |
|
Torchmeta: A meta-learning library for pytorch
arXiv preprint arXiv:1909.06576, 2019 View on Google Scholar ↗ |
2019 | 52 | 73.5% |
|
Entropy Regularization.
Semi-supervised learning, 151-168, 2006 View on Google Scholar ↗ |
2006 | 114 | 73.5% |
|
Dynamic neural turing machine with continuous and discrete addressing schemes
Neural computation 30 (4), 857-884, 2018 View on Google Scholar ↗ |
2018 | 61 | 73.3% |
|
Unsupervised models of images by spike-and-slab RBMs
ICML, 2011 View on Google Scholar ↗ |
2011 | 98 | 73.1% |
|
How to initialize your network? robust initialization for weightnorm & resnets
Advances in Neural Information Processing Systems 32, 2019 View on Google Scholar ↗ |
2019 | 51 | 73.1% |
|
Deep learning (no. 2)
MIT press Cambridge, 2016 View on Google Scholar ↗ |
2016 | 73 | 73.0% |
|
On the challenges of physical implementations of RBMs
Proceedings of the AAAI Conference on Artificial Intelligence 28 (1), 2014 View on Google Scholar ↗ |
2014 | 83 | 72.9% |
|
Quickly generating representative samples from an RBM-derived process
Neural computation 23 (8), 2058-2073, 2011 View on Google Scholar ↗ |
2011 | 97 | 72.9% |
|
Variational causal networks: Approximate bayesian inference over causal structures
arXiv preprint arXiv:2106.07635, 2021 View on Google Scholar ↗ |
2021 | 31 | 72.7% |
|
Using a financial training criterion rather than a prediction criterion
International journal of neural systems 8 (04), 433-443, 1997 View on Google Scholar ↗ |
1997 | 107 | 72.6% |
|
A field guide to dynamical recurrent neural networks
chapter Gradient Flow in Recurrent Nets: The Difficulty of Learning Long …, 2001 View on Google Scholar ↗ |
2001 | 117 | 72.4% |
|
Sequence modeling: recurrent and recursive nets
Deep learning, 367-415, 2016 View on Google Scholar ↗ |
2016 | 71 | 72.4% |
|
6.5 Back-propagation and other differentiation algorithms
Deep learning, 200-220, 2016 View on Google Scholar ↗ |
2016 | 71 | 72.4% |
|
Retrognn: fast estimation of synthesizability for virtual screening and de novo design by learning from slow retrosynthesis software
Journal of Chemical Information and Modeling 62 (10), 2293-2300, 2022 View on Google Scholar ↗ |
2022 | 19 | 72.2% |
|
Shape, contour and grouping in computer vision
Lecture Notes in Computer Science 1681, 319-345, 1999 View on Google Scholar ↗ |
1999 | 110 | 72.2% |
|
Fortified networks: Improving the robustness of deep networks by modeling the manifold of hidden representations
arXiv preprint arXiv:1804.02485, 2018 View on Google Scholar ↗ |
2018 | 58 | 72.2% |
|
3rd International Conference on Learning Representations
ICLR, San Diego, 2015 View on Google Scholar ↗ |
2015 | 76 | 72.1% |
|
Improving speech recognition by revising gated recurrent units
arXiv preprint arXiv:1710.00641, 2017 View on Google Scholar ↗ |
2017 | 65 | 72.1% |
|
Advances in neural information processing systems
Curran Associates Incorporation 24, 2011 View on Google Scholar ↗ |
2011 | 93 | 72.0% |
|
Systematic evaluation of causal discovery in visual model based reinforcement learning
arXiv preprint arXiv:2107.00848, 2021 View on Google Scholar ↗ |
2021 | 30 | 71.9% |
|
Incorporating Functional Knowledge in Neural Networks.
Journal of Machine Learning Research 10 (6), 2009 View on Google Scholar ↗ |
2009 | 99 | 71.8% |
|
Deep learning
Nature 521 (7553), 436-444, 2015 View on Google Scholar ↗ |
2015 | 75 | 71.8% |
|
Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network
arXiv preprint arXiv:2305.19366, 2023 View on Google Scholar ↗ |
2023 | 11 | 71.7% |
|
Stochastic Generative Flow Networks
arXiv preprint arXiv:2302.09465, 2023 View on Google Scholar ↗ |
2023 | 11 | 71.7% |
|
Reinforcement learning with competitive ensembles of information-constrained primitives
arXiv preprint arXiv:1906.10667, 2019 View on Google Scholar ↗ |
2019 | 48 | 71.7% |
|
Dynamic neural turing machine with soft and hard addressing schemes
arXiv preprint arXiv:1607.00036, 2016 View on Google Scholar ↗ |
2016 | 68 | 71.4% |
|
Compositional generalization in a deep seq2seq model by separating syntax and semantics
arXiv preprint arXiv:1904.09708, 2019 View on Google Scholar ↗ |
2019 | 47 | 71.2% |
|
Equivalence of equilibrium propagation and recurrent backpropagation
Neural computation 31 (2), 312-329, 2019 View on Google Scholar ↗ |
2019 | 47 | 71.2% |
|
Learning dynamics model in reinforcement learning by incorporating the long term future
arXiv preprint arXiv:1903.01599, 2019 View on Google Scholar ↗ |
2019 | 47 | 71.2% |
|
Dynamic inference with neural interpreters
Advances in Neural Information Processing Systems 34, 10985-10998, 2021 View on Google Scholar ↗ |
2021 | 29 | 71.1% |
|
From machine learning to robotics: challenges and opportunities for embodied intelligence
arXiv preprint arXiv:2110.15245, 2021 View on Google Scholar ↗ |
2021 | 29 | 71.1% |
|
Interactive language learning by question answering
arXiv preprint arXiv:1908.10909, 2019 View on Google Scholar ↗ |
2019 | 46 | 70.6% |
|
Convolutional networks for images
Speech, and Time-Series, 1995 View on Google Scholar ↗ |
1995 | 87 | 70.2% |
|
Twin networks: Matching the future for sequence generation
arXiv preprint arXiv:1708.06742, 2017 View on Google Scholar ↗ |
2017 | 60 | 70.2% |
|
Artificial neural networks and their application to sequence recognition
View on Google Scholar ↗ |
1991 | 80 | 70.2% |
|
Learning from unexpected events in the neocortical microcircuit
BioRxiv, 2021.01. 15.426915, 2021 View on Google Scholar ↗ |
2021 | 28 | 70.2% |
|
A consciousness-inspired planning agent for model-based reinforcement learning
Advances in neural information processing systems 34, 1569-1581, 2021 View on Google Scholar ↗ |
2021 | 28 | 70.2% |
|
Adding noise to the input of a model trained with a regularized objective
arXiv preprint arXiv:1104.3250, 2011 View on Google Scholar ↗ |
2011 | 86 | 70.1% |
|
Training methods for adaptive boosting of neural networks
Advances in neural information processing systems 10, 1997 View on Google Scholar ↗ |
1997 | 94 | 70.1% |
|
Aaron Courville deep learning
MIT press, 2016 View on Google Scholar ↗ |
2016 | 64 | 70.0% |
|
Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets
arXiv preprint arXiv:2305.17010, 2023 View on Google Scholar ↗ |
2023 | 10 | 69.6% |
|
International institutions for advanced AI
arXiv preprint arXiv:2307.04699, 2023 View on Google Scholar ↗ |
2023 | 10 | 69.6% |
|
Faenet: Frame averaging equivariant gnn for materials modeling
International Conference on Machine Learning, 9013-9033, 2023 View on Google Scholar ↗ |
2023 | 10 | 69.6% |
|
Machines who learn
Scientific American 314 (6), 44-51, 2016 View on Google Scholar ↗ |
2016 | 63 | 69.6% |
|
MAgnet: Mesh agnostic neural PDE solver
Advances in Neural Information Processing Systems 35, 31972-31985, 2022 View on Google Scholar ↗ |
2022 | 17 | 69.5% |
|
Visualizing the consequences of climate change using cycle-consistent adversarial networks
arXiv preprint arXiv:1905.03709, 2019 View on Google Scholar ↗ |
2019 | 44 | 69.5% |
|
Infomask: Masked variational latent representation to localize chest disease
Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd …, 2019 View on Google Scholar ↗ |
2019 | 44 | 69.5% |
|
Quadratic polynomials learn better image features
Technical report, 1337, 2009 View on Google Scholar ↗ |
2009 | 89 | 69.5% |
|
Fraternal dropout
arXiv preprint arXiv:1711.00066, 2017 View on Google Scholar ↗ |
2017 | 58 | 69.4% |
|
The Z-coder adaptive binary coder
Proceedings DCC'98 Data Compression Conference (Cat. No. 98TB100225), 13-22, 1998 View on Google Scholar ↗ |
1998 | 92 | 69.3% |
|
Slow, decorrelated features for pretraining complex cell-like networks
Advances in neural information processing systems 22, 2009 View on Google Scholar ↗ |
2009 | 88 | 69.3% |
|
Mollifying networks
arXiv preprint arXiv:1608.04980, 2016 View on Google Scholar ↗ |
2016 | 62 | 69.2% |
|
Proceedings of the 25th international conference on Machine learning
ACM, 2008 View on Google Scholar ↗ |
2008 | 90 | 69.2% |
|
3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings
arXiv preprint arXiv:1412.6980, 2015 View on Google Scholar ↗ |
2015 | 67 | 69.0% |
|
Online continual learning with no task boundaries
arXiv preprint arXiv:1903.08671 3, 2, 2019 View on Google Scholar ↗ |
2019 | 43 | 69.0% |
|
Spike-and-slab sparse coding for unsupervised feature discovery
arXiv preprint arXiv:1201.3382, 2012 View on Google Scholar ↗ |
2012 | 78 | 68.8% |
|
Fitnets: Hints for thin deep nets. arXiv 2014
arXiv preprint arXiv:1412.6550, 2014 View on Google Scholar ↗ |
2014 | 70 | 68.7% |
|
Monaural singing voice separation with skip-filtering connections and recurrent inference of time-frequency mask
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018 View on Google Scholar ↗ |
2018 | 50 | 68.6% |
|
Updates of equilibrium prop match gradients of backprop through time in an RNN with static input
Advances in neural information processing systems 32, 2019 View on Google Scholar ↗ |
2019 | 42 | 68.3% |
|
Embedding word similarity with neural machine translation
arXiv preprint arXiv:1412.6448, 2014 View on Google Scholar ↗ |
2014 | 69 | 68.3% |
|
Properties from mechanisms: an equivariance perspective on identifiable representation learning
arXiv preprint arXiv:2110.15796, 2021 View on Google Scholar ↗ |
2021 | 26 | 68.3% |
|
The handbook of brain theory and neural networks. chapter Convolutional Networks for Images, Speech, and Time Series
MIT Press, Cambridge, MA, USA 3, 255-258, 1998 View on Google Scholar ↗ |
1998 | 87 | 68.2% |
|
Quadratic features and deep architectures for chunking
Proceedings of Human Language Technologies: The 2009 Annual Conference of …, 2009 View on Google Scholar ↗ |
2009 | 84 | 68.2% |
|
Adaboosting neural networks: Application to on-line character recognition
Artificial Neural Networks—ICANN'97: 7th International Conference Lausanne …, 1997 View on Google Scholar ↗ |
1997 | 85 | 68.1% |
|
Generative augmented flow networks
arXiv preprint arXiv:2210.03308, 2022 View on Google Scholar ↗ |
2022 | 16 | 68.0% |
|
Lookback for learning to branch
arXiv preprint arXiv:2206.14987, 2022 View on Google Scholar ↗ |
2022 | 16 | 68.0% |
|
Variational walkback: Learning a transition operator as a stochastic recurrent net
Advances in Neural Information Processing Systems 30, 2017 View on Google Scholar ↗ |
2017 | 54 | 67.6% |
|
Credit assignment through time: Alternatives to backpropagation
Advances in neural information processing systems 6, 1993 View on Google Scholar ↗ |
1993 | 70 | 67.4% |
|
Continuous domain adaptation with variational domain-agnostic feature replay
arXiv preprint arXiv:2003.04382, 2020 View on Google Scholar ↗ |
2020 | 34 | 67.4% |
|
Using artificial intelligence to visualize the impacts of climate change
IEEE Computer Graphics and Applications 41 (1), 8-14, 2021 View on Google Scholar ↗ |
2021 | 25 | 67.3% |
|
Spectral clustering and kernel PCA are learning eigenfunctions
CIRANO, 2003 View on Google Scholar ↗ |
2003 | 90 | 67.2% |
|
Use of genetic programming for the search of a new learning rule for neural networks
Proceedings of the First IEEE Conference on Evolutionary Computation. IEEE …, 1994 View on Google Scholar ↗ |
1994 | 74 | 67.1% |
|
A structured self-attentive sentence embedding. arXiv 2017
arXiv preprint arXiv:1703.03130, 2017 View on Google Scholar ↗ |
2017 | 53 | 67.1% |
|
Equilibrium propagation with continual weight updates
arXiv preprint arXiv:2005.04168, 2020 View on Google Scholar ↗ |
2020 | 33 | 66.7% |
|
Probabilistic planning with sequential monte carlo methods
International Conference on Learning Representations, 2018 View on Google Scholar ↗ |
2018 | 46 | 66.5% |
|
Unifying generative models with gflownets
arXiv preprint arXiv:2209.02606, 2022 View on Google Scholar ↗ |
2022 | 15 | 66.5% |
|
Towards scaling difference target propagation by learning backprop targets
International Conference on Machine Learning, 5968-5987, 2022 View on Google Scholar ↗ |
2022 | 15 | 66.5% |
|
Multi-scale feature learning dynamics: Insights for double descent
International Conference on Machine Learning, 17669-17690, 2022 View on Google Scholar ↗ |
2022 | 15 | 66.5% |
|
Continuous-time meta-learning with forward mode differentiation
arXiv preprint arXiv:2203.01443, 2022 View on Google Scholar ↗ |
2022 | 15 | 66.5% |
|
Quasi-Geodesic Neural Learning Algorithms Over the Orthogonal Group: A Tutorial.
Journal of Machine Learning Research 6 (5), 2005 View on Google Scholar ↗ |
2005 | 83 | 66.4% |
|
Selective small molecule peptidomimetic ligands of TrkC and TrkA receptors afford discrete or complete neurotrophic activities
Chemistry & biology 12 (9), 1015-1028, 2005 View on Google Scholar ↗ |
2005 | 83 | 66.4% |
|
A network of deep neural networks for distant speech recognition
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017 View on Google Scholar ↗ |
2017 | 51 | 66.1% |
|
Generative adversarial nets. arXiv
arXiv preprint arXiv:1406.2661, 2014 View on Google Scholar ↗ |
2014 | 63 | 66.0% |
|
Special issue on neural networks for data mining and knowledge discovery
IEEE Transactions on Neural Networks 11 (3), 545-822, 2000 View on Google Scholar ↗ |
2000 | 85 | 65.5% |
|
h-detach: Modifying the LSTM gradient towards better optimization
arXiv preprint arXiv:1810.03023, 2018 View on Google Scholar ↗ |
2018 | 44 | 65.4% |
|
On the spectral bias of deep neural networks
arXiv preprint arXiv:1806.08734 4, 2018 View on Google Scholar ↗ |
2018 | 44 | 65.4% |
|
Learning deep representations by mutual information estimation and maximization
arXiv e-prints, arXiv: 1808.06670, 2018 View on Google Scholar ↗ |
2018 | 44 | 65.4% |
|
Learning causal models online
arXiv preprint arXiv:2006.07461, 2020 View on Google Scholar ↗ |
2020 | 31 | 65.1% |
|
Learning concept embeddings for query expansion by quantum entropy minimization
Proceedings of the AAAI Conference on Artificial Intelligence 28 (1), 2014 View on Google Scholar ↗ |
2014 | 60 | 64.8% |
|
Building robust ensembles via margin boosting
International Conference on Machine Learning, 26669-26692, 2022 View on Google Scholar ↗ |
2022 | 14 | 64.7% |
|
Independently controllable features
arXiv preprint arXiv:1708.01289, 2017 View on Google Scholar ↗ |
2017 | 48 | 64.6% |
|
Distributional GFlowNets with Quantile Flows
arXiv preprint arXiv:2302.05793, 2023 View on Google Scholar ↗ |
2023 | 8 | 64.5% |
|
Simulation-free Schr\" odinger bridges via score and flow matching
arXiv preprint arXiv:2307.03672, 2023 View on Google Scholar ↗ |
2023 | 8 | 64.5% |
|
A data-efficient framework for training and sim-to-real transfer of navigation policies
2019 International Conference on Robotics and Automation (ICRA), 782-788, 2019 View on Google Scholar ↗ |
2019 | 36 | 64.4% |
|
Empirical evaluation of convolutional RBMs for vision
Technical Report 1327, Département d’Informatique et de Recherche …, 2008 View on Google Scholar ↗ |
2008 | 73 | 64.3% |
|
On computational power and the order-chaos phase transition in reservoir computing
NIPS Foundation 21, 1425-1432, 2009 View on Google Scholar ↗ |
2009 | 70 | 64.1% |
|
Dendritic error backpropagation in deep cortical microcircuits
arXiv preprint arXiv:1801.00062, 2017 View on Google Scholar ↗ |
2017 | 47 | 64.0% |
|
Transformers with competitive ensembles of independent mechanisms
arXiv preprint arXiv:2103.00336, 2021 View on Google Scholar ↗ |
2021 | 22 | 64.0% |
|
Non-local manifold parzen windows
Advances in neural information processing systems 18, 2005 View on Google Scholar ↗ |
2005 | 73 | 63.7% |
|
Greedy spectral embedding
International Workshop on Artificial Intelligence and Statistics, 253-260, 2005 View on Google Scholar ↗ |
2005 | 73 | 63.7% |
|
Nature
Nature 521 (7553), 436, 2015 View on Google Scholar ↗ |
2015 | 54 | 63.7% |
|
Independently controllable factors
arXiv preprint arXiv:1708.01289, 2017 View on Google Scholar ↗ |
2017 | 46 | 63.5% |
|
The bottleneck simulator: A model-based deep reinforcement learning approach
Journal of Artificial Intelligence Research 69, 571-612, 2020 View on Google Scholar ↗ |
2020 | 29 | 63.3% |
|
Towards a biologically plausible backprop
arXiv preprint arXiv:1602.05179 914, 2016 View on Google Scholar ↗ |
2016 | 49 | 63.3% |
|
Diffusion of context and credit information in Markovian models
Journal of Artificial Intelligence Research 3, 249-270, 1995 View on Google Scholar ↗ |
1995 | 61 | 63.2% |
|
Continuous neural networks
Artificial Intelligence and Statistics, 404-411, 2007 View on Google Scholar ↗ |
2007 | 70 | 63.2% |
|
Word normalization for online handwritten word recognition
Proceedings of the 12th IAPR International Conference on Pattern Recognition …, 1994 View on Google Scholar ↗ |
1994 | 61 | 63.2% |
|
Iterative neural autoregressive distribution estimator nade-k
Advances in neural information processing systems 27, 2014 View on Google Scholar ↗ |
2014 | 56 | 63.0% |
|
Independently controllable features
arXiv preprint arXiv:1703.07718, 2017 View on Google Scholar ↗ |
2017 | 45 | 62.9% |
|
Closure: Assessing systematic generalization of clevr models
arXiv preprint arXiv:1912.05783, 2019 View on Google Scholar ↗ |
2019 | 34 | 62.9% |
|
Saliency is a possible red herring when diagnosing poor generalization
arXiv preprint arXiv:1910.00199, 2019 View on Google Scholar ↗ |
2019 | 34 | 62.9% |
|
FL Games: A federated learning framework for distribution shifts
arXiv preprint arXiv:2205.11101, 2022 View on Google Scholar ↗ |
2022 | 13 | 62.7% |
|
Object-centric compositional imagination for visual abstract reasoning
ICLR2022 Workshop on the Elements of Reasoning: Objects, Structure and Causality, 2022 View on Google Scholar ↗ |
2022 | 13 | 62.7% |
|
On the morality of artificial intelligence [Commentary]
IEEE Technology and Society Magazine 39 (1), 16-25, 2020 View on Google Scholar ↗ |
2020 | 28 | 62.4% |
|
Cost functions and model combination for VaR-based asset allocation using neural networks
IEEE Transactions on Neural Networks 12 (4), 890-906, 2001 View on Google Scholar ↗ |
2001 | 70 | 62.3% |
|
High-dimensional sequence transduction
2013 IEEE international conference on acoustics, speech and signal …, 2013 View on Google Scholar ↗ |
2013 | 56 | 62.2% |
|
Reseg: A recurrent neural network for object segmentation
arXiv preprint arXiv:1511.07053, 2015 View on Google Scholar ↗ |
2015 | 51 | 62.2% |
|
Not all neural embeddings are born equal
arXiv preprint arXiv:1410.0718, 2014 View on Google Scholar ↗ |
2014 | 54 | 62.1% |
|
Deep learning, volume 1
MIT press Cambridge, 2016 View on Google Scholar ↗ |
2016 | 46 | 61.6% |
|
Bias in Estimating the Variance of K-Fold Cross-Validation
Statistical modeling and analysis for complex data problems, 75-95, 2005 View on Google Scholar ↗ |
2005 | 66 | 61.6% |
|
Z-coder: a fast adaptive binary arithmetic coder
US Patent 6,225,925, 2001 View on Google Scholar ↗ |
2001 | 66 | 61.2% |
|
GEO-Bench: Toward Foundation Models for Earth Monitoring
arXiv preprint arXiv:2306.03831, 2023 View on Google Scholar ↗ |
2023 | 7 | 61.2% |
|
Thompson sampling for improved exploration in GFlowNets
arXiv preprint arXiv:2306.17693, 2023 View on Google Scholar ↗ |
2023 | 7 | 61.2% |
|
Generalization of equilibrium propagation to vector field dynamics
arXiv preprint arXiv:1808.04873, 2018 View on Google Scholar ↗ |
2018 | 37 | 61.0% |
|
Speech and speaker recognition from raw waveform with sincnet
arXiv preprint arXiv:1812.05920, 2018 View on Google Scholar ↗ |
2018 | 37 | 61.0% |
|
Bias learning, knowledge sharing
IEEE Transactions on Neural Networks 14 (4), 748-765, 2003 View on Google Scholar ↗ |
2003 | 67 | 60.9% |
|
Posterior samples of source galaxies in strong gravitational lenses with score-based priors
arXiv preprint arXiv:2211.03812, 2022 View on Google Scholar ↗ |
2022 | 12 | 60.7% |
|
Early inference in energy-based models approximates back-propagation
arXiv preprint arXiv:1510.02777, 2015 View on Google Scholar ↗ |
2015 | 48 | 60.6% |
|
Batch-normalized joint training for DNN-based distant speech recognition
2016 IEEE Spoken Language Technology Workshop (SLT), 28-34, 2016 View on Google Scholar ↗ |
2016 | 44 | 60.5% |
|
Reinforcement learning for sustainable agriculture
ICML 2019 Workshop Climate Change: How Can AI Help, 2019 View on Google Scholar ↗ |
2019 | 31 | 60.5% |
|
A highly adaptive acoustic model for accurate multi-dialect speech recognition
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 View on Google Scholar ↗ |
2019 | 31 | 60.5% |
|
Towards standardization of data licenses: The montreal data license
arXiv preprint arXiv:1903.12262, 2019 View on Google Scholar ↗ |
2019 | 31 | 60.5% |
|
Large-scale kernel machines
Scaling Learning Algorithms towards AI. MIT Press, Cambridge, 2007 View on Google Scholar ↗ |
2007 | 61 | 60.2% |
|
Deep learning for NLP
Tutorial at Association of Computational Logistics (ACL), 2012 View on Google Scholar ↗ |
2012 | 55 | 60.2% |
|
Variational bi-lstms
arXiv preprint arXiv:1711.05717, 2017 View on Google Scholar ↗ |
2017 | 40 | 59.9% |
|
Extensions to metric based model selection
The Journal of Machine Learning Research 3, 1209-1227, 2003 View on Google Scholar ↗ |
2003 | 62 | 59.4% |
|
STDP as presynaptic activity times rate of change of postsynaptic activity
arXiv preprint arXiv:1509.05936, 2015 View on Google Scholar ↗ |
2015 | 45 | 58.9% |
|
Experiments on the application of IOHMMs to model financial returns series
IEEE Transactions on Neural Networks 12 (1), 113-123, 2001 View on Google Scholar ↗ |
2001 | 59 | 58.9% |
|
Scaling up spike-and-slab models for unsupervised feature learning
IEEE transactions on pattern analysis and machine intelligence 35 (8), 1902-1914, 2012 View on Google Scholar ↗ |
2012 | 52 | 58.8% |
|
Towards gene expression convolutions using gene interaction graphs
arXiv preprint arXiv:1806.06975, 2018 View on Google Scholar ↗ |
2018 | 34 | 58.7% |
|
Universal successor representations for transfer reinforcement learning
arXiv preprint arXiv:1804.03758, 2018 View on Google Scholar ↗ |
2018 | 34 | 58.7% |
|
The benefits of over-parameterization at initialization in deep ReLU networks
arXiv preprint arXiv:1901.03611, 2019 View on Google Scholar ↗ |
2019 | 29 | 58.7% |
|
A learning-based algorithm to quickly compute good primal solutions for stochastic integer programs
Integration of Constraint Programming, Artificial Intelligence, and …, 2020 View on Google Scholar ↗ |
2020 | 24 | 58.4% |
|
Clustering is efficient for approximate maximum inner product search
arXiv preprint arXiv:1507.05910, 2015 View on Google Scholar ↗ |
2015 | 44 | 58.4% |
|
Bayesian learning of causal structure and mechanisms with gflownets and variational bayes
arXiv preprint arXiv:2211.02763, 2022 View on Google Scholar ↗ |
2022 | 11 | 58.2% |
|
Predictive inference with feature conformal prediction
arXiv preprint arXiv:2210.00173, 2022 View on Google Scholar ↗ |
2022 | 11 | 58.2% |
|
Z-coder: fast adaptive binary arithmetic coder
US Patent 6,188,334, 2001 View on Google Scholar ↗ |
2001 | 56 | 57.9% |
|
Texture modeling with convolutional spike-and-slab RBMs and deep extensions
Artificial Intelligence and Statistics, 415-423, 2013 View on Google Scholar ↗ |
2013 | 47 | 57.8% |
|
Spectral dimensionality reduction
Feature Extraction: Foundations and Applications, 519-550, 2006 View on Google Scholar ↗ |
2006 | 55 | 57.7% |
|
Programmable execution of multi-layered networks for automatic speech recognition
Communications of the ACM 32 (2), 195-199, 1989 View on Google Scholar ↗ |
1989 | 41 | 57.6% |
|
Gflowout: Dropout with generative flow networks
International Conference on Machine Learning, 21715-21729, 2023 View on Google Scholar ↗ |
2023 | 6 | 57.4% |
|
Bitpruning: Learning bitlengths for aggressive and accurate quantization
arXiv preprint arXiv:2002.03090, 2020 View on Google Scholar ↗ |
2020 | 23 | 57.3% |
|
Compositional generalization by factorizing alignment and translation
Proceedings of the 58th Annual Meeting of the Association for Computational …, 2020 View on Google Scholar ↗ |
2020 | 23 | 57.3% |
|
NU-GAN: High resolution neural upsampling with GAN
arXiv preprint arXiv:2010.11362, 2020 View on Google Scholar ↗ |
2020 | 23 | 57.3% |
|
et HINTON, Geoffrey
Deep learning. nature 521 (7553), 436, 2015 View on Google Scholar ↗ |
2015 | 42 | 57.2% |
|
Modeling the long term future in model-based reinforcement learning
International Conference on Learning Representations, 2018 View on Google Scholar ↗ |
2018 | 32 | 57.1% |
|
Finding flatter minima with sgd
View on Google Scholar ↗ |
2018 | 32 | 57.1% |
|
An EM algorithm for asynchronous input/output hidden Markov models
International Conference On Neural Information Processing 78, 328-334, 1996 View on Google Scholar ↗ |
1996 | 46 | 57.1% |
|
Unifying likelihood-free inference with black-box optimization and beyond
arXiv preprint arXiv:2110.03372, 2021 View on Google Scholar ↗ |
2021 | 17 | 57.1% |
|
Learning the dynamic nature of speech with back-propagation for sequences
Pattern recognition letters 13 (5), 375-385, 1992 View on Google Scholar ↗ |
1992 | 43 | 57.0% |
|
Phonetically motivated acoustic parameters for continuous speech recognition using artificial neural networks
Speech Communication 11 (2-3), 261-271, 1992 View on Google Scholar ↗ |
1992 | 43 | 57.0% |
|
On the search for new learning rules for ANNs
Neural Processing Letters 2, 26-30, 1995 View on Google Scholar ↗ |
1995 | 45 | 56.8% |
|
Learning tags that vary within a song
ISMIR, Utrecht, Netherlands, 2010 View on Google Scholar ↗ |
2010 | 50 | 56.6% |
|
The representational geometry of word meanings acquired by neural machine translation models
Machine Translation 31, 3-18, 2017 View on Google Scholar ↗ |
2017 | 35 | 56.5% |
|
Nonlocal estimation of manifold structure
Neural Computation 18 (10), 2509-2528, 2006 View on Google Scholar ↗ |
2006 | 52 | 56.5% |
|
A preliminary evaluation of word representations for named-entity recognition
NIPS Workshop on Grammar Induction, Representation of Language and Language …, 2009 View on Google Scholar ↗ |
2009 | 50 | 56.4% |
|
Exponentially increasing the capacity-to-computation ratio for conditional computation in deep learning
arXiv preprint arXiv:1406.7362, 2014 View on Google Scholar ↗ |
2014 | 43 | 56.4% |
|
Untangling tradeoffs between recurrence and self-attention in artificial neural networks
Advances in Neural Information Processing Systems 33, 19443-19454, 2020 View on Google Scholar ↗ |
2020 | 22 | 56.1% |
|
Speaker independent speech recognition with neural networks and speech knowledge
Advances in neural information processing systems 2, 1989 View on Google Scholar ↗ |
1989 | 38 | 56.1% |
|
The spike-and-slab RBM and extensions to discrete and sparse data distributions
IEEE transactions on pattern analysis and machine intelligence 36 (9), 1874-1887, 2013 View on Google Scholar ↗ |
2013 | 44 | 56.1% |
|
Caelli, Terry, 249
View on Google Scholar ↗ |
2007 | 50 | 55.8% |
|
On neural architecture inductive biases for relational tasks
arXiv preprint arXiv:2206.05056, 2022 View on Google Scholar ↗ |
2022 | 10 | 55.7% |
|
Evaluating generalization in gflownets for molecule design
ICLR2022 Machine Learning for Drug Discovery, 2022 View on Google Scholar ↗ |
2022 | 10 | 55.7% |
|
Gradient flow in recurrent nets: the difficulty of learning long-term dependencies.(2001)
Cited on, 114, 2001 View on Google Scholar ↗ |
2001 | 49 | 55.4% |
|
Editorial introduction to the neural networks special issue on deep learning of representations
Neural Networks 64 (C), 1-3, 2015 View on Google Scholar ↗ |
2015 | 39 | 55.2% |
|
Scaling large learning problems with hard parallel mixtures
International Journal of pattern recognition and artificial intelligence 17 …, 2003 View on Google Scholar ↗ |
2003 | 50 | 55.2% |
|
Pattern recognition and neural networks
The Handbook of Brain Theory and Neural Networks. MIT Press, Cambridge, MA, 1995 View on Google Scholar ↗ |
1995 | 41 | 55.0% |
|
Deriving differential target propagation from iterating approximate inverses
arXiv preprint arXiv:2007.15139, 2020 View on Google Scholar ↗ |
2020 | 21 | 54.9% |
|
RetroGNN: Approximating retrosynthesis by graph neural networks for de novo drug design
arXiv preprint arXiv:2011.13042, 2020 View on Google Scholar ↗ |
2020 | 21 | 54.9% |
|
The variational bandwidth bottleneck: Stochastic evaluation on an information budget
arXiv preprint arXiv:2004.11935, 2020 View on Google Scholar ↗ |
2020 | 21 | 54.9% |
|
Module for constructing trainable modular network in which each module inputs and outputs data structured as a graph
US Patent 6,128,606, 2000 View on Google Scholar ↗ |
2000 | 49 | 54.8% |
|
Gradmask: Reduce overfitting by regularizing saliency
arXiv preprint arXiv:1904.07478, 2019 View on Google Scholar ↗ |
2019 | 25 | 54.6% |
|
MaD TwinNet: Masker-denoiser architecture with twin networks for monaural sound source separation
2018 International Joint Conference on Neural Networks (IJCNN), 1-8, 2018 View on Google Scholar ↗ |
2018 | 29 | 54.6% |
|
深度学习
Ren min you dian chu ban she, 2017 View on Google Scholar ↗ |
2017 | 32 | 54.2% |
|
Efficient recognition of immunoglobulin domains from amino acid sequences using a neural network
Bioinformatics 6 (4), 319-324, 1990 View on Google Scholar ↗ |
1990 | 35 | 53.8% |
|
On the learning dynamics of deep neural networks
arXiv preprint arXiv:1809.06848, 2018 View on Google Scholar ↗ |
2018 | 28 | 53.7% |
|
Compositional attention: Disentangling search and retrieval
arXiv preprint arXiv:2110.09419, 2021 View on Google Scholar ↗ |
2021 | 15 | 53.6% |
|
An analysis of the adaptation speed of causal models
International Conference on Artificial Intelligence and Statistics, 775-783, 2021 View on Google Scholar ↗ |
2021 | 15 | 53.6% |
|
SampleRNN: An unconditional end-to-end neural audio generation model (2016)
arXiv preprint ArXiv:1612.07837, 2021 View on Google Scholar ↗ |
2021 | 15 | 53.6% |
|
Predicting infectiousness for proactive contact tracing
arXiv preprint arXiv:2010.12536, 2020 View on Google Scholar ↗ |
2020 | 20 | 53.6% |
|
A hybrid coder for hidden Markov models using a recurrent neural networks
International Conference on Acoustics, Speech, and Signal Processing, 537-540, 1990 View on Google Scholar ↗ |
1990 | 34 | 53.3% |
|
Regeneration learning: A learning paradigm for data generation
arXiv preprint arXiv:2301.08846, 2023 View on Google Scholar ↗ |
2023 | 5 | 52.8% |
|
Sources of richness and ineffability for phenomenally conscious states
arXiv preprint arXiv:2302.06403, 2023 View on Google Scholar ↗ |
2023 | 5 | 52.8% |
|
Commonsense mining as knowledge base completion? A study on the impact of novelty
arXiv preprint arXiv:1804.09259, 2018 View on Google Scholar ↗ |
2018 | 27 | 52.7% |
|
Estimating car insurance premia: A case study in high-dimensional data inference
Advances in Neural Information Processing Systems 14, 2001 View on Google Scholar ↗ |
2001 | 42 | 52.6% |
|
Icentia11k: An unsupervised representation learning dataset for arrhythmia subtype discovery
arXiv preprint arXiv:1910.09570, 2019 View on Google Scholar ↗ |
2019 | 23 | 52.4% |
|
Universal successor features for transfer reinforcement learning
arXiv preprint arXiv:2001.04025, 2020 View on Google Scholar ↗ |
2020 | 19 | 52.1% |
|
Unsupervised sense disambiguation using bilingual probabilistic models
Proceedings of the 42nd Annual Meeting of the Association for Computational …, 2004 View on Google Scholar ↗ |
2004 | 43 | 52.0% |
|
On the iterative refinement of densely connected representation levels for semantic segmentation
Proceedings of the IEEE conference on computer vision and pattern …, 2018 View on Google Scholar ↗ |
2018 | 26 | 51.7% |
|
Phonetically-based multi-layered neural networks for vowel classification
Speech Communication 9 (1), 15-29, 1990 View on Google Scholar ↗ |
1990 | 30 | 50.9% |
|
15 improving first and second-order methods by modeling uncertainty
Optimization for machine learning, 403, 2011 View on Google Scholar ↗ |
2011 | 38 | 50.9% |
|
Large-Scale Learning of Embeddings with Reconstruction Sampling.
ICML, 945-952, 2011 View on Google Scholar ↗ |
2011 | 38 | 50.9% |
|
Focused hierarchical rnns for conditional sequence processing
International Conference on Machine Learning, 2554-2563, 2018 View on Google Scholar ↗ |
2018 | 25 | 50.6% |
|
Width of minima reached by stochastic gradient descent is influenced by learning rate to batch size ratio
Artificial Neural Networks and Machine Learning–ICANN 2018: 27th …, 2018 View on Google Scholar ↗ |
2018 | 25 | 50.6% |
|
On training recurrent neural networks for lifelong learning
CoRR, abs/1811.07017, 2018 View on Google Scholar ↗ |
2018 | 25 | 50.6% |
|
Deep learning: systemy uczące się
Wydawnictwo Naukowe PWN SA, 2020 View on Google Scholar ↗ |
2020 | 18 | 50.6% |
|
Learning eigenfunctions of similarity: linking spectral clustering and kernel PCA
Technical Report 1232, Departement d’Informatique et Recherche Oprationnelle …, 2003 View on Google Scholar ↗ |
2003 | 39 | 50.6% |
|
Statistical learning algorithms applied to automobile insurance ratemaking
CAS Forum 1 (1), 179-214, 2003 View on Google Scholar ↗ |
2003 | 39 | 50.6% |
|
Task loss estimation for sequence prediction
arXiv preprint arXiv:1511.06456, 2015 View on Google Scholar ↗ |
2015 | 32 | 50.3% |
|
Discriminative Non-negative Matrix Factorization for Multiple Pitch Estimation.
ISMIR, 205-210, 2012 View on Google Scholar ↗ |
2012 | 36 | 50.2% |
|
How transferable are features in convolutional neural network acoustic models across languages?
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 View on Google Scholar ↗ |
2019 | 21 | 50.1% |
|
Contextual tag inference
ACM Transactions on Multimedia Computing, Communications, and Applications …, 2011 View on Google Scholar ↗ |
2011 | 36 | 49.7% |
|
Adaptive boosting of neural networks for character recognition
Advances in Neural Information Processing 10 (1997), 1997 View on Google Scholar ↗ |
1997 | 34 | 49.7% |
|
Discrete factorial representations as an abstraction for goal conditioned reinforcement learning
arXiv preprint arXiv:2211.00247, 2022 View on Google Scholar ↗ |
2022 | 8 | 49.6% |
|
Robust and controllable object-centric learning through energy-based models
arXiv preprint arXiv:2210.05519, 2022 View on Google Scholar ↗ |
2022 | 8 | 49.6% |
|
Understanding the difficulty of training deep feedforward neural networks. 2010
International Conference on Artificial Intelligence and Statistics 1, 2018 View on Google Scholar ↗ |
2018 | 24 | 49.6% |
|
Predicting solution summaries to integer linear programs under imperfect information with machine learning
arXiv preprint arXiv:1807.11876, 2018 View on Google Scholar ↗ |
2018 | 24 | 49.6% |
|
The first conversational intelligence challenge
The NIPS'17 Competition: Building Intelligent Systems, 25-46, 2018 View on Google Scholar ↗ |
2018 | 24 | 49.6% |
|
Regularized auto-encoders estimate local statistics
arXiv preprint arXiv:1211.4246, 1-17, 2012 View on Google Scholar ↗ |
2012 | 35 | 49.5% |
|
Use of neural networks for the recognition of place of articulation
ICASSP-88., International Conference on Acoustics, Speech, and Signal …, 1988 View on Google Scholar ↗ |
1988 | 28 | 49.5% |
|
Adaptive parallel tempering for stochastic maximum likelihood learning of RBMs
arXiv preprint arXiv:1012.3476, 2010 View on Google Scholar ↗ |
2010 | 36 | 49.4% |
|
Diffusion of credit in Markovian models
Advances in Neural Information Processing Systems 7, 1994 View on Google Scholar ↗ |
1994 | 30 | 49.1% |
|
Maxout networks (2013)
arXiv preprint arXiv:1302.4389, 2017 View on Google Scholar ↗ |
2017 | 26 | 49.0% |
|
Bidirectional helmholtz machines
International Conference on Machine Learning, 2511-2519, 2016 View on Google Scholar ↗ |
2016 | 28 | 48.7% |
|
Unsupervised learning of semantics of object detections for scene categorization
Pattern Recognition Applications and Methods: International Conference …, 2015 View on Google Scholar ↗ |
2015 | 30 | 48.6% |
|
On tracking the partition function
Advances in neural information processing systems 24, 2011 View on Google Scholar ↗ |
2011 | 34 | 48.5% |
|
Adaptive drift-diffusion process to learn time intervals
arXiv preprint arXiv:1103.2382, 2011 View on Google Scholar ↗ |
2011 | 33 | 48.0% |
|
A hybrid pareto mixture for conditional asymmetric fat-tailed distributions
IEEE transactions on neural networks 20 (7), 1087-1101, 2009 View on Google Scholar ↗ |
2009 | 33 | 47.8% |
|
Tractable multivariate binary density estimation and the restricted Boltzmann forest
Neural computation 22 (9), 2285-2307, 2010 View on Google Scholar ↗ |
2010 | 33 | 47.6% |
|
Building musically-relevant audio features through multiple timescale representations
View on Google Scholar ↗ |
2012 | 32 | 47.5% |
|
DynGFN: Bayesian Dynamic Causal Discovery using Generative Flow Networks
arXiv preprint arXiv:2302.04178, 2023 View on Google Scholar ↗ |
2023 | 4 | 47.4% |
|
Attention Schema in Neural Agents
arXiv preprint arXiv:2305.17375, 2023 View on Google Scholar ↗ |
2023 | 4 | 47.4% |
|
Proactive Contact Tracing
PLOS Digital Health 2 (3), e0000199, 2023 View on Google Scholar ↗ |
2023 | 4 | 47.4% |
|
RECOVER identifies synergistic drug combinations in vitro through sequential model optimization
Cell Reports Methods 3 (10), 2023 View on Google Scholar ↗ |
2023 | 4 | 47.4% |
|
A two-stream continual learning system with variational domain-agnostic feature replay
IEEE Transactions on Neural Networks and Learning Systems 33 (9), 4466-4478, 2021 View on Google Scholar ↗ |
2021 | 12 | 47.4% |
|
6th International Conference on Learning Representations, ICLR
Vancouver, BC, Canada, 2018 View on Google Scholar ↗ |
2018 | 22 | 47.3% |
|
Browsing through high quality document images with DjVu
Proceedings IEEE International Forum on Research and Technology Advances in …, 1998 View on Google Scholar ↗ |
1998 | 29 | 46.8% |
|
Implementations of algorithms for hyper-parameter optimization
NIPS Workshop on Bayesian optimization 29, 2011 View on Google Scholar ↗ |
2011 | 31 | 46.6% |
|
Brain inspired reinforcement learning
Advances in neural information processing systems 17, 2004 View on Google Scholar ↗ |
2004 | 32 | 46.5% |
|
Training a neural network with a financial criterion rather than a prediction criterion
Decision Technologies for Financial Engineering: Proceedings of the Fourth …, 1997 View on Google Scholar ↗ |
1997 | 28 | 46.4% |
|
The effect of task and training on intermediate representations in convolutional neural networks revealed with modified RV similarity analysis
arXiv preprint arXiv:1912.02260, 2019 View on Google Scholar ↗ |
2019 | 18 | 46.1% |
|
Weakly-supervised knowledge graph alignment with adversarial learning
arXiv preprint arXiv:1907.03179, 2019 View on Google Scholar ↗ |
2019 | 18 | 46.1% |
|
Joint training deep boltzmann machines for classification
arXiv preprint arXiv:1301.3568, 2013 View on Google Scholar ↗ |
2013 | 29 | 46.1% |
|
Recurrent neural networks for adaptive temporal processing
Universitá di Firenze, 1993 View on Google Scholar ↗ |
1993 | 23 | 46.0% |
|
Latent state marginalization as a low-cost approach for improving exploration
arXiv preprint arXiv:2210.00999, 2022 View on Google Scholar ↗ |
2022 | 7 | 46.0% |
|
Recover: sequential model optimization platform for combination drug repurposing identifies novel synergistic compounds in vitro
arXiv preprint arXiv:2202.04202, 2022 View on Google Scholar ↗ |
2022 | 7 | 46.0% |
|
Adaptive discrete communication bottlenecks with dynamic vector quantization
arXiv preprint arXiv:2202.01334, 2022 View on Google Scholar ↗ |
2022 | 7 | 46.0% |
|
Controlled sparsity via constrained optimization or: How i learned to stop tuning penalties and love constraints
Advances in Neural Information Processing Systems 35, 1253-1266, 2022 View on Google Scholar ↗ |
2022 | 7 | 46.0% |
|
Exploiting syntactic structure for better language modeling: A syntactic distance approach
arXiv preprint arXiv:2005.05864, 2020 View on Google Scholar ↗ |
2020 | 15 | 45.8% |
|
S2rms: Spatially structured recurrent modules
arXiv preprint arXiv:2007.06533, 2020 View on Google Scholar ↗ |
2020 | 15 | 45.8% |
|
Support vector machines for improving the classification of brain PET images
Medical Imaging 1998: Image Processing 3338, 264-273, 1998 View on Google Scholar ↗ |
1998 | 27 | 45.6% |
|
Augmented functional time series representation and forecasting with Gaussian processes
Advances in neural information processing systems 20, 2007 View on Google Scholar ↗ |
2007 | 30 | 45.4% |
|
Learning from partial labels with minimum entropy
Centre interuniversitaire de recherche en analyse des organisations (CIRANO), 2004 View on Google Scholar ↗ |
2004 | 30 | 45.3% |
|
Metric-free natural gradient for joint-training of boltzmann machines
arXiv preprint arXiv:1301.3545, 2013 View on Google Scholar ↗ |
2013 | 28 | 45.3% |
|
Discriminative feature and model design for automatic speech recognition.
Eurospeech, 1997 View on Google Scholar ↗ |
1997 | 26 | 45.2% |
|
Alternative time representation in dopamine models
Journal of computational neuroscience 28, 107-130, 2010 View on Google Scholar ↗ |
2010 | 29 | 45.1% |
|
Climategan: Raising climate change awareness by generating images of floods
arXiv preprint arXiv:2110.02871, 2021 View on Google Scholar ↗ |
2021 | 11 | 45.1% |
|
Hypothesis testing for cross-validation
Montreal Universite de Montreal, Operationnelle DdIeR 1285, 2006 View on Google Scholar ↗ |
2006 | 29 | 45.0% |
|
The effects of negative adaptation in model-agnostic meta-learning
arXiv preprint arXiv:1812.02159, 2018 View on Google Scholar ↗ |
2018 | 20 | 45.0% |
|
Deep learning 1 (2)
MIT press Cambridge, 2016 View on Google Scholar ↗ |
2016 | 24 | 44.9% |
|
An EM approach to grammatical inference: input/output HMMs
Proceedings of the 12th IAPR International Conference on Pattern Recognition …, 1994 View on Google Scholar ↗ |
1994 | 24 | 44.8% |
|
Learning deep architectures for AI. Found Trends Mach Learn 2 (1): 1–127
View on Google Scholar ↗ |
2009 | 28 | 44.7% |
|
Learning deep architectures for AI. Foundations and Trends® in Machine Learning, 2 (1), 1-127
Google Scholar Google Scholar Digital Library Digital Library, 2009 View on Google Scholar ↗ |
2009 | 28 | 44.7% |
|
Bounding the test log-likelihood of generative models
arXiv preprint arXiv:1311.6184, 2013 View on Google Scholar ↗ |
2013 | 27 | 44.6% |
|
Efficient EM training of Gaussian mixtures with missing data
arXiv preprint arXiv:1209.0521, 2012 View on Google Scholar ↗ |
2012 | 28 | 44.5% |
|
Quantized guided pruning for efficient hardware implementations of deep neural networks
2020 18th IEEE International New Circuits and Systems Conference (NEWCAS …, 2020 View on Google Scholar ↗ |
2020 | 14 | 44.0% |
|
Deep learning (adaptive computation and machine learning series)
The MIT Press, 2016 View on Google Scholar ↗ |
2016 | 23 | 43.9% |
|
A robust adaptive stochastic gradient method for deep learning
2017 International Joint Conference on Neural Networks (IJCNN), 125-132, 2017 View on Google Scholar ↗ |
2017 | 21 | 43.8% |
|
Graph attention networks
ICLR. Petar Velickovic Guillem Cucurull Arantxa Casanova Adriana Romero …, 2018 View on Google Scholar ↗ |
2018 | 19 | 43.7% |
|
Locally Linear Embedding for dimensionality reduction in QSAR
Journal of Computer-Aided Molecular Design 18, 475-482, 2004 View on Google Scholar ↗ |
2004 | 27 | 43.5% |
|
Unlearning for better mixing
Universite de Montreal/DIRO, 2010 View on Google Scholar ↗ |
2010 | 26 | 42.9% |
|
Learning the 2-d topology of images
Advances in Neural Information Processing Systems 20, 2007 View on Google Scholar ↗ |
2007 | 26 | 42.8% |
|
Learning deep architectures for AI. Found Trends Mach Learn 2: 1–127
View on Google Scholar ↗ |
2009 | 25 | 42.6% |
|
Exploration-driven representation learning in reinforcement learning
ICML 2021 Workshop on Unsupervised Reinforcement Learning, 2021 View on Google Scholar ↗ |
2021 | 10 | 42.5% |
|
Learning hierarchical structures on-the-fly with a recurrent-recursive model for sequences
Proceedings of The Third Workshop on Representation Learning for NLP, 154-158, 2018 View on Google Scholar ↗ |
2018 | 18 | 42.4% |
|
A deep reinforcement learning chatbot (short version)
arXiv preprint arXiv:1801.06700, 2018 View on Google Scholar ↗ |
2018 | 18 | 42.4% |
|
Density-sensitive metrics and kernels
Snowbird Learning Workshop, 2003 View on Google Scholar ↗ |
2003 | 24 | 42.4% |
|
A neural support vector network architecture with adaptive kernels
Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural …, 2000 View on Google Scholar ↗ |
2000 | 24 | 42.3% |
|
Stateful active facilitator: Coordination and environmental heterogeneity in cooperative multi-agent reinforcement learning
arXiv preprint arXiv:2210.03022, 2022 View on Google Scholar ↗ |
2022 | 6 | 42.2% |
|
Temporal latent bottleneck: Synthesis of fast and slow processing mechanisms in sequence learning
Advances in Neural Information Processing Systems 35, 10505-10520, 2022 View on Google Scholar ↗ |
2022 | 6 | 42.2% |
|
Temporal abstractions-augmented temporally contrastive learning: An alternative to the Laplacian in RL
Uncertainty in Artificial Intelligence, 641-651, 2022 View on Google Scholar ↗ |
2022 | 6 | 42.2% |
|
On the generalization and adaption performance of causal models
arXiv preprint arXiv:2206.04620, 2022 View on Google Scholar ↗ |
2022 | 6 | 42.2% |
|
PhAST: Physics-aware, scalable, and task-specific GNNs for accelerated catalyst design
arXiv preprint arXiv:2211.12020, 2022 View on Google Scholar ↗ |
2022 | 6 | 42.2% |
|
Evaluating benchmark problems by random guessing
A Field Guide to Dynamical Recurrent Networks, 231-235, 2001 View on Google Scholar ↗ |
2001 | 23 | 42.1% |
|
Feedforward initialization for fast inference of deep generative networks is biologically plausible
arXiv preprint arXiv:1606.01651, 2016 View on Google Scholar ↗ |
2016 | 21 | 41.8% |
|
Information matrices and generalization
arXiv preprint arXiv:1906.07774, 2019 View on Google Scholar ↗ |
2019 | 15 | 41.7% |
|
New distributed probabilistic language models
Technical Report 1215, Dept. IRO, Université de Montréal, 2002 View on Google Scholar ↗ |
2002 | 23 | 41.6% |
|
Robust regression with asymmetric heavy-tail noise distributions
Neural Computation 14 (10), 2469-2496, 2002 View on Google Scholar ↗ |
2002 | 23 | 41.6% |
|
Plan, attend, generate: Planning for sequence-to-sequence models
Advances in Neural Information Processing Systems 30, 2017 View on Google Scholar ↗ |
2017 | 19 | 41.5% |
|
On the challenge of learning complex functions
Progress in Brain Research 165, 521-534, 2007 View on Google Scholar ↗ |
2007 | 24 | 41.4% |
|
Stochastic ratio matching of RBMs for sparse high-dimensional inputs
Advances in Neural Information Processing Systems 26, 2013 View on Google Scholar ↗ |
2013 | 23 | 41.3% |
|
Generalization in machine learning via analytical learning theory
arXiv preprint arXiv:1802.07426, 2018 View on Google Scholar ↗ |
2018 | 17 | 41.2% |
|
Learning semantic representations of objects and their parts
Machine learning 94, 281-301, 2014 View on Google Scholar ↗ |
2014 | 22 | 40.9% |
|
Deep directed generative autoencoders
arXiv preprint arXiv:1410.0630, 2014 View on Google Scholar ↗ |
2014 | 22 | 40.9% |
|
Automated Detection of Anatomical Landmarks During Colonoscopy Using a Deep Learning Model
Journal of the Canadian Association of Gastroenterology, gwad017, 2023 View on Google Scholar ↗ |
2023 | 3 | 40.7% |
|
What if We Enrich day-ahead Solar Irradiance Time Series Forecasting with Spatio-Temporal Context?
arXiv preprint arXiv:2306.01112, 2023 View on Google Scholar ↗ |
2023 | 3 | 40.7% |
|
A neuronal least-action principle for real-time learning in cortical circuits
bioRxiv, 2023.03. 25.534198, 2023 View on Google Scholar ↗ |
2023 | 3 | 40.7% |
|
Learning to scale logits for temperature-conditional gflownets
arXiv preprint arXiv:2310.02823, 2023 View on Google Scholar ↗ |
2023 | 3 | 40.7% |
|
Responses of pyramidal cell somata and apical dendrites in mouse visual cortex over multiple days
Scientific Data 10 (1), 287, 2023 View on Google Scholar ↗ |
2023 | 3 | 40.7% |
|
Local search gflownets
arXiv preprint arXiv:2310.02710, 2023 View on Google Scholar ↗ |
2023 | 3 | 40.7% |
|
AI and Catastrophic Risk
Journal of Democracy 34 (4), 111-121, 2023 View on Google Scholar ↗ |
2023 | 3 | 40.7% |
|
The effect of diversity in meta-learning
Proceedings of the AAAI Conference on Artificial Intelligence 37 (7), 8396-8404, 2023 View on Google Scholar ↗ |
2023 | 3 | 40.7% |
|
BabyAI 1.1
arXiv e-prints, arXiv: 2007.12770, 2020 View on Google Scholar ↗ |
2020 | 12 | 40.3% |
|
Learning invariant features through local space contraction
arXiv preprint arXiv:1104.4153, 2011 View on Google Scholar ↗ |
2011 | 22 | 40.0% |
|
Topic Segmentation: A First Stage to Dialog-Based Information Extraction.
NLPRS, 273-279, 2001 View on Google Scholar ↗ |
2001 | 20 | 40.0% |
|
Structured sparsity inducing adaptive optimizers for deep learning
arXiv preprint arXiv:2102.03869, 2021 View on Google Scholar ↗ |
2021 | 9 | 39.8% |
|
Twin regularization for online speech recognition
arXiv preprint arXiv:1804.05374, 2018 View on Google Scholar ↗ |
2018 | 16 | 39.8% |
|
Manifold mixup: learning better representations by interpolating hidden states
stat 1050, 4, 2018 View on Google Scholar ↗ |
2018 | 16 | 39.8% |
|
Deep self-taught learning for handwritten character recognition
arXiv preprint arXiv:1009.3589, 2010 View on Google Scholar ↗ |
2010 | 22 | 39.8% |
|
Speaker normalization and automatic speech recognition using spectral lines and neural networks
Proceedings of the 1988 Connectionist Models Summer School, 388-397, 1988 View on Google Scholar ↗ |
1988 | 16 | 39.6% |
|
Natural gradient revisited
View on Google Scholar ↗ |
2013 | 21 | 39.5% |
|
Z-coder: a fast adaptive binary arithmetic coder
US Patent 6,281,817, 2001 View on Google Scholar ↗ |
2001 | 19 | 39.2% |
|
Adasecant: robust adaptive secant method for stochastic gradient
arXiv preprint arXiv:1412.7419, 2014 View on Google Scholar ↗ |
2014 | 20 | 38.9% |
|
Handling asynchronous or missing data with recurrent networks
International Journal of Computational Intelligence and Organizations 1 (3 …, 1998 View on Google Scholar ↗ |
1998 | 18 | 38.7% |
|
Representation learning
Deep learning, 528-559, 2016 View on Google Scholar ↗ |
2016 | 18 | 38.5% |
|
Use of multi-layered networks for coding speech with phonetic features
Advances in neural information processing systems 1, 1988 View on Google Scholar ↗ |
1988 | 15 | 38.5% |
|
Dynamic frame skipping for fast speech recognition in recurrent neural network based acoustic models
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018 View on Google Scholar ↗ |
2018 | 15 | 38.4% |
|
Quantized guided pruning for efficient hardware implementations of convolutional neural networks
arXiv preprint arXiv:1812.11337, 2018 View on Google Scholar ↗ |
2018 | 15 | 38.4% |
|
COVI-AgentSim: an agent-based model for evaluating methods of digital contact tracing
arXiv preprint arXiv:2010.16004, 2020 View on Google Scholar ↗ |
2020 | 11 | 38.2% |
|
Machine learning for glacier monitoring in the Hindu Kush Himalaya
arXiv preprint arXiv:2012.05013, 2020 View on Google Scholar ↗ |
2020 | 11 | 38.2% |
|
An EM approach to learning sequential behavior
Advances in Neural Information Processing Systems 7, 1994 View on Google Scholar ↗ |
1994 | 16 | 38.0% |
|
Large-Scale Algorithms.
Semi-supervised learning, 332-341, 2006 View on Google Scholar ↗ |
2006 | 19 | 38.0% |
|
Neural network-Gaussian mixture hybrid for speech recognition or density estimation
Advances in Neural Information Processing Systems 4, 1991 View on Google Scholar ↗ |
1991 | 15 | 37.9% |
|
Scaling up deep learning
Proceedings of the 20th ACM SIGKDD international conference on Knowledge …, 2014 View on Google Scholar ↗ |
2014 | 19 | 37.9% |
|
Conditioning and time representation in long short-term memory networks
Biological cybernetics 108, 23-48, 2014 View on Google Scholar ↗ |
2014 | 19 | 37.9% |
|
Kernel matching pursuit
Machine Learning 48 (1), 2, 2002 View on Google Scholar ↗ |
2002 | 18 | 37.8% |
|
Continuous optimization of hyper-parameters
Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural …, 2000 View on Google Scholar ↗ |
2000 | 18 | 37.8% |
|
How to construct deep recurrent neural networks
CoRR, abs/1312.6026, 2013 View on Google Scholar ↗ |
2013 | 19 | 37.6% |
|
Speech recognition method and apparatus
US Patent 11,282,501, 2022 View on Google Scholar ↗ |
2022 | 5 | 37.6% |
|
Object-centric causal representation learning
NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations, 2022 View on Google Scholar ↗ |
2022 | 5 | 37.6% |
|
Agnostic physics-driven deep learning
arXiv preprint arXiv:2205.15021, 2022 View on Google Scholar ↗ |
2022 | 5 | 37.6% |
|
Speechbrain: A general-purpose speech toolkit
View on Google Scholar ↗ |
2022 | 5 | 37.6% |
|
Neural networks for speech recognition
Spoken Dialogues with Computers, 311-361, 1998 View on Google Scholar ↗ |
1998 | 16 | 37.0% |
|
On training deep Boltzmann machines
arXiv preprint arXiv:1203.4416, 2012 View on Google Scholar ↗ |
2012 | 19 | 36.9% |
|
La révolution de l’apprentissage profond
Interstices, 2019 View on Google Scholar ↗ |
2019 | 12 | 36.7% |
|
Advances in Neural Information Processing Systems
Proceedings of the 19th Annual Conference on Neural Information Processing …, 2005 View on Google Scholar ↗ |
2005 | 17 | 36.5% |
|
Image segmentation by iterative inference from conditional score estimation
arXiv preprint arXiv:1705.07450, 2017 View on Google Scholar ↗ |
2017 | 15 | 36.5% |
|
Actual: Actor-critic under adversarial learning
arXiv preprint arXiv:1711.04755, 2017 View on Google Scholar ↗ |
2017 | 15 | 36.5% |
|
Deep learning: Adaptive computation and machine learning
MIT Press, 2017 View on Google Scholar ↗ |
2017 | 15 | 36.5% |
|
On catastrophic interference in atari 2600 games
arXiv preprint arXiv:2002.12499, 2020 View on Google Scholar ↗ |
2020 | 10 | 36.0% |
|
Automated segmentation of cortical layers in BigBrain reveals divergent cortical and laminar thickness gradients in sensory and motor cortices
PLOS BIOLOGY 18 (4), e3000678, 2020 View on Google Scholar ↗ |
2020 | 10 | 36.0% |
|
Factorizing declarative and procedural knowledge in structured, dynamical environments
International Conference on Learning Representations, 2020 View on Google Scholar ↗ |
2020 | 10 | 36.0% |
|
A large-scale, open-domain, mixed-interface dialogue-based ITS for STEM
Artificial Intelligence in Education: 21st International Conference, AIED …, 2020 View on Google Scholar ↗ |
2020 | 10 | 36.0% |
|
Sparse attentive backtracking: Long-range credit assignment in recurrent networks
arXiv preprint arXiv:1711.02326, 2017 View on Google Scholar ↗ |
2017 | 14 | 35.1% |
|
Twin networks: Using the future as a regularizer
CoRR, abs/1708.06742, 2017 View on Google Scholar ↗ |
2017 | 14 | 35.1% |
|
Gibbsnet: Iterative adversarial inference for deep graphical models
Advances in Neural Information Processing Systems 30, 2017 View on Google Scholar ↗ |
2017 | 14 | 35.1% |
|
Generalizable features from unsupervised learning
arXiv preprint arXiv:1612.03809, 2016 View on Google Scholar ↗ |
2016 | 15 | 35.0% |
|
Conditional computation for continual learning
arXiv preprint arXiv:1906.06635, 2019 View on Google Scholar ↗ |
2019 | 11 | 34.9% |
|
Autotagging music with conditional restricted Boltzmann machines
arXiv preprint arXiv:1103.2832, 2011 View on Google Scholar ↗ |
2011 | 16 | 34.5% |
|
Curran Associates
Inc.: Red Hook, NY, USA 21, 2009 View on Google Scholar ↗ |
2009 | 15 | 34.3% |
|
Detonation classification from acoustic signature with the restricted Boltzmann machine
Computational Intelligence 28 (2), 261-288, 2012 View on Google Scholar ↗ |
2012 | 16 | 33.9% |
|
An objective function for STDP
arXiv preprint arXiv:1509.05936 5 (6.2), 6.3, 2015 View on Google Scholar ↗ |
2015 | 15 | 33.8% |
|
Visual concept reasoning networks
Proceedings of the AAAI Conference on Artificial Intelligence 35 (9), 8172-8180, 2021 View on Google Scholar ↗ |
2021 | 7 | 33.8% |
|
HBert+ BiasCorp--Fighting Racism on the Web
arXiv preprint arXiv:2104.02242, 2021 View on Google Scholar ↗ |
2021 | 7 | 33.8% |
|
Generating multiscale amorphous molecular structures using deep learning: a study in 2D
The Journal of Physical Chemistry Letters 11 (20), 8532-8537, 2020 View on Google Scholar ↗ |
2020 | 9 | 33.7% |
|
Keep drawing it: Iterative language-based image generation and editing
arXiv preprint arXiv:1811.09845 2, 2018 View on Google Scholar ↗ |
2018 | 12 | 33.6% |
|
How can deep learning advance computational modeling of sensory information processing?
arXiv preprint arXiv:1810.08651, 2018 View on Google Scholar ↗ |
2018 | 12 | 33.6% |
|
Quick training of probabilistic neural nets by sampling
Proc. 9th International Workshop on Artificial Intelligence and Statistics …, 2003 View on Google Scholar ↗ |
2003 | 13 | 33.4% |
|
Nicholas L ́eonard, and Aaron Courville
Estimating or propagating gradients through stochasticneurons for …, 2013 View on Google Scholar ↗ |
2013 | 15 | 33.3% |
|
Radial basis functions for speech recognition
Speech Recognition and Understanding: Recent Advances, Trends and …, 1992 View on Google Scholar ↗ |
1992 | 11 | 33.0% |
|
Reinforced imitation in heterogeneous action space
arXiv preprint arXiv:1904.03438, 2019 View on Google Scholar ↗ |
2019 | 10 | 33.0% |
|
Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv: 14090473. 2014
Search in, 2019 View on Google Scholar ↗ |
2019 | 10 | 33.0% |
|
Parallel stochastic gradient descent
CIAR Summer School, Toronto, 2007 View on Google Scholar ↗ |
2007 | 14 | 32.9% |
|
Input decay: Simple and effective soft variable selection
IJCNN'01. International Joint Conference on Neural Networks. Proceedings …, 2001 View on Google Scholar ↗ |
2001 | 12 | 32.7% |
|
Training methods for adaptive boosting of neural networks for character recognition
Advances in Neural Information Processing Systems 10, 1998 View on Google Scholar ↗ |
1998 | 12 | 32.7% |
|
Efficient non-parametric function induction in semi-supervised learning
CIRANO, 2004 View on Google Scholar ↗ |
2004 | 13 | 32.5% |
|
AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N
arXiv preprint arXiv:2208.07004, 2022 View on Google Scholar ↗ |
2022 | 4 | 32.5% |
|
Latent bottlenecked attentive neural processes
arXiv preprint arXiv:2211.08458, 2022 View on Google Scholar ↗ |
2022 | 4 | 32.5% |
|
Inductive Biases for Relational Tasks
ICLR2022 Workshop on the Elements of Reasoning: Objects, Structure and Causality, 2022 View on Google Scholar ↗ |
2022 | 4 | 32.5% |
|
PMFL: Partial Meta-Federated Learning for heterogeneous tasks and its applications on real-world medical records
2022 IEEE International Conference on Big Data (Big Data), 4453-4462, 2022 View on Google Scholar ↗ |
2022 | 4 | 32.5% |
|
Designing biological sequences via meta-reinforcement learning and Bayesian optimization
arXiv preprint arXiv:2209.06259, 2022 View on Google Scholar ↗ |
2022 | 4 | 32.5% |
|
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. dec 2014
URL http://arxiv. org/abs/1412.3555, 2014 View on Google Scholar ↗ |
2014 | 14 | 32.4% |
|
On the equivalence between deep nade and generative stochastic networks
Machine Learning and Knowledge Discovery in Databases: European Conference …, 2014 View on Google Scholar ↗ |
2014 | 14 | 32.4% |
|
Practical methodology
Deep Learning, 416-437, 2016 View on Google Scholar ↗ |
2016 | 13 | 32.3% |
|
The octopus approach to the Alexa competition: A deep ensemble-based socialbot
Alexa Prize Proceedings, 2017 View on Google Scholar ↗ |
2017 | 12 | 32.2% |
|
Multiscale sequence modeling with a learned dictionary
arXiv preprint arXiv:1707.00762, 2017 View on Google Scholar ↗ |
2017 | 12 | 32.2% |
|
Char2Wav: End-to-end speech synthesis
ICLR, 2017 View on Google Scholar ↗ |
2017 | 12 | 32.2% |
|
Deep learning architectures for AI
Found. Trends Mach. Learn 2 (1), 1-127, 2009 View on Google Scholar ↗ |
2009 | 13 | 32.1% |
|
Montréal Declaration for a responsible development of artificial intelligence
Announced at the conclusion of the Forum on the Socially Responsible …, 2018 View on Google Scholar ↗ |
2018 | 11 | 32.0% |
|
Modularity matters: learning invariant relational reasoning tasks
arXiv preprint arXiv:1806.06765, 2018 View on Google Scholar ↗ |
2018 | 11 | 32.0% |
|
A3t: Adversarially augmented adversarial training
arXiv preprint arXiv:1801.04055, 2018 View on Google Scholar ↗ |
2018 | 11 | 32.0% |
|
Implicit density estimation by local moment matching to sample from auto-encoders
arXiv preprint arXiv:1207.0057, 2012 View on Google Scholar ↗ |
2012 | 14 | 31.7% |
|
Improving gradient-guided nested sampling for posterior inference
arXiv preprint arXiv:2312.03911, 2023 View on Google Scholar ↗ |
2023 | 2 | 31.7% |
|
Diffusion generative flow samplers: Improving learning signals through partial trajectory optimization
arXiv preprint arXiv:2310.02679, 2023 View on Google Scholar ↗ |
2023 | 2 | 31.7% |
|
Generative Flow Networks: a Markov Chain Perspective
arXiv preprint arXiv:2307.01422, 2023 View on Google Scholar ↗ |
2023 | 2 | 31.7% |
|
MixupE: Understanding and improving Mixup from directional derivative perspective
Uncertainty in Artificial Intelligence, 2597-2607, 2023 View on Google Scholar ↗ |
2023 | 2 | 31.7% |
|
Causal machine learning for single-cell genomics
arXiv preprint arXiv:2310.14935, 2023 View on Google Scholar ↗ |
2023 | 2 | 31.7% |
|
Multi-Fidelity Active Learning with GFlowNets
arXiv preprint arXiv:2306.11715, 2023 View on Google Scholar ↗ |
2023 | 2 | 31.7% |
|
Reusable Slotwise Mechanisms
arXiv preprint arXiv:2302.10503, 2023 View on Google Scholar ↗ |
2023 | 2 | 31.7% |
|
Crystal-gfn: sampling crystals with desirable properties and constraints
arXiv preprint arXiv:2310.04925, 2023 View on Google Scholar ↗ |
2023 | 2 | 31.7% |
|
Generative AI models should include detection mechanisms as a condition for public release
Ethics and Information Technology 25 (4), 55, 2023 View on Google Scholar ↗ |
2023 | 2 | 31.7% |
|
A memory-efficient adaptive Huffman coding algorithm for very large sets of symbols
Proceedings DCC'98 Data Compression Conference (Cat. No. 98TB100225), 568, 1998 View on Google Scholar ↗ |
1998 | 11 | 31.5% |
|
Gradient-based learning applied to document recognitionntion
Intelligent Signal Processing, 306-351, 2001 View on Google Scholar ↗ |
2001 | 11 | 31.5% |
|
Locally weighted full covariance gaussian density estimation
CIRANO, 2004 View on Google Scholar ↗ |
2004 | 12 | 31.4% |
|
Systematicity in a Recurrent Neural Network by Factorizing Syntax and Semantics.
CogSci, 2020 View on Google Scholar ↗ |
2020 | 8 | 31.3% |
|
Combating false negatives in adversarial imitation learning
arXiv preprint arXiv:2002.00412, 2020 View on Google Scholar ↗ |
2020 | 8 | 31.3% |
|
Using Simulated Data to Generate Images of Climate Change
arXiv preprint arXiv:2001.09531, 2020 View on Google Scholar ↗ |
2020 | 8 | 31.3% |
|
Highres-net: Multi-frame super-resolution by recursive fusion
View on Google Scholar ↗ |
2019 | 9 | 31.0% |
|
Statistical machine learning algorithms for target classification from acoustic signature
Proc. MSS Battlespace Acoust. Magn. Sensors, 1-18, 2009 View on Google Scholar ↗ |
2009 | 12 | 31.0% |
|
Deep Learing of representations: Looking forward in: Proceedings of the 1st international Confernece on Statistical Language and Speech Processing SLSP’13
Springer, Tarragone, Spain, 2013 View on Google Scholar ↗ |
2013 | 13 | 31.0% |
|
Data-driven execution of multi-layered networks for automatic speech recognition
Proceedings of the Seventh AAAI National Conference on Artificial …, 1988 View on Google Scholar ↗ |
1988 | 9 | 30.4% |
|
A memory-efficient Huffman adaptive coding algorithm for very large sets of symbols revisited
Université de Montréal, Rapport technique 1095, 1997 View on Google Scholar ↗ |
1997 | 10 | 30.3% |
|
Binary pseudowavelets and applications to bilevel image processing
Proceedings DCC'99 Data Compression Conference (Cat. No. PR00096), 364-373, 1999 View on Google Scholar ↗ |
1999 | 10 | 30.0% |
|
Learning deep architectures for AI Foundations and Trends in Machine Learning, 2, 1-127
View on Google Scholar ↗ |
2009 | 11 | 29.8% |
|
Unsupervised and Transfer Learning under Uncertainty-From Object Detections to Scene Categorization.
ICPRAM, 345-354, 2013 View on Google Scholar ↗ |
2013 | 12 | 29.7% |
|
Learned-norm pooling for deep neural networks
arXiv preprint arXiv:1311.1780, 2013 View on Google Scholar ↗ |
2013 | 12 | 29.7% |
|
Z-coder: a fast adaptive binary arithmetic coder
US Patent 6,476,740, 2002 View on Google Scholar ↗ |
2002 | 10 | 29.6% |
|
NYU-MILA neural machine translation systems for WMT’16
Proceedings of the First Conference on Machine Translation: Volume 2, Shared …, 2016 View on Google Scholar ↗ |
2016 | 11 | 29.4% |
|
Plan, attend, generate: Character-level neural machine translation with planning
Proceedings of the 2nd Workshop on Representation Learning for NLP, 228-234, 2017 View on Google Scholar ↗ |
2017 | 10 | 29.0% |
|
STDP as presynaptic activity times rate of change of postsynaptic activity approximates back-propagation
Neural Computation 10, 2017 View on Google Scholar ↗ |
2017 | 10 | 29.0% |
|
Suitability of V1 energy models for object classification
Neural Computation 23 (3), 774-790, 2011 View on Google Scholar ↗ |
2011 | 11 | 29.0% |
|
Phonetically-based multi-layered networks for acoustic property extraction and automatic speech recognition
Speech Communication 9 (1), 15-30, 1990 View on Google Scholar ↗ |
1990 | 8 | 28.9% |
|
Lagrangian dynamics of dendritic microcircuits enables real-time backpropagation of errors
target 100 (1), 2, 2019 View on Google Scholar ↗ |
2019 | 8 | 28.9% |
|
Generalization of a parametric learning rule
ICANN’93: Proceedings of the International Conference on Artificial Neural …, 1993 View on Google Scholar ↗ |
1993 | 8 | 28.6% |
|
An infinite factor model hierarchy via a noisy-or mechanism
Advances in neural information processing systems 22, 2009 View on Google Scholar ↗ |
2009 | 10 | 28.5% |
|
Continuous control with deep reinforcement learning
Found. Trends® Mach. Learn 2, 1-127, 2009 View on Google Scholar ↗ |
2009 | 10 | 28.5% |
|
On the generalization capability of multi-layered networks in the extraction of speech properties
Proceedings of the 11th international joint conference on Artificial …, 1989 View on Google Scholar ↗ |
1989 | 8 | 28.3% |
|
Convolutional neural networks for Images, Speech and Time Series
AT&T Laboratories, 1-14, 1995 View on Google Scholar ↗ |
1995 | 8 | 27.9% |
|
Deep learning for automatic summary scoring
Proceedings of the workshop on automatic text summarization, 17-28, 2011 View on Google Scholar ↗ |
2011 | 10 | 27.7% |
|
Oracle performance for visual captioning
arXiv preprint arXiv:1511.04590, 2015 View on Google Scholar ↗ |
2015 | 10 | 27.2% |
|
Learning deep architectures for ai, Found, Trends Mach. Learn, 2 (1), 1-127, 2009
View on Google Scholar ↗ |
2009 | 9 | 27.2% |
|
andJason Weston
Curriculum learning. InICML 4, 2009 View on Google Scholar ↗ |
2009 | 9 | 27.2% |
|
Deep tempering
arXiv preprint arXiv:1410.0123, 2014 View on Google Scholar ↗ |
2014 | 10 | 27.2% |
|
Deep learning and cultural evolution
Proceedings of the companion publication of the 2014 annual conference on …, 2014 View on Google Scholar ↗ |
2014 | 10 | 27.2% |
|
Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv. org
arXiv preprint arXiv:1406.1078, 2014 View on Google Scholar ↗ |
2014 | 10 | 27.2% |
|
Multimodal transitions for generative stochastic networks
arXiv preprint arXiv:1312.5578, 2013 View on Google Scholar ↗ |
2013 | 10 | 27.0% |
|
Inference for the Generalization Error
Centre interuniversitaire de recherche en analyse des organisations (CIRANO), 1999 View on Google Scholar ↗ |
1999 | 8 | 26.9% |
|
Training neural networks to recognize speech increased their correspondence to the human auditory pathway but did not yield a shared hierarchy of acoustic features
BioRxiv, 2021.01. 26.428323, 2021 View on Google Scholar ↗ |
2021 | 5 | 26.8% |
|
Neural function modules with sparse arguments: A dynamic approach to integrating information across layers
International Conference on Artificial Intelligence and Statistics, 919-927, 2021 View on Google Scholar ↗ |
2021 | 5 | 26.8% |
|
Découpage thématique des conversations: un outil d’aide à l’extraction
TALN 2002, 2002 View on Google Scholar ↗ |
2002 | 8 | 26.7% |
|
State-reification networks: Improving generalization by modeling the distribution of hidden representations
International Conference on Machine Learning, 3622-3631, 2019 View on Google Scholar ↗ |
2019 | 7 | 26.6% |
|
On the morality of artificial intelligence
arXiv preprint arXiv:1912.11945, 2019 View on Google Scholar ↗ |
2019 | 7 | 26.6% |
|
Learning the arrow of time for problems in reinforcement learning
International Conference on Learning Representations, 2019 View on Google Scholar ↗ |
2019 | 7 | 26.6% |
|
Discrete Compositional Representations as an Abstraction for Goal Conditioned Reinforcement Learning
Advances in Neural Information Processing Systems 35, 3885-3899, 2022 View on Google Scholar ↗ |
2022 | 3 | 26.5% |
|
A neural network to detect homologies in proteins
Advances in Neural Information Processing Systems 2, 1989 View on Google Scholar ↗ |
1989 | 7 | 26.2% |
|
Speech coding with multi-layer networks
International Conference on Acoustics, Speech, and Signal Processing,, 164-167, 1989 View on Google Scholar ↗ |
1989 | 7 | 26.2% |
|
Understanding the difficulty of training deep feedforward neural networks
Thirteenth International Conference on Artificial Intelligence and …, 2010 View on Google Scholar ↗ |
2010 | 9 | 26.1% |
|
Establishing an evaluation metric to quantify climate change image realism
Machine Learning: Science and Technology 1 (2), 025005, 2020 View on Google Scholar ↗ |
2020 | 6 | 25.9% |
|
Factorized embeddings learns rich and biologically meaningful embedding spaces using factorized tensor decomposition
Bioinformatics 36 (Supplement_1), i417-i426, 2020 View on Google Scholar ↗ |
2020 | 6 | 25.9% |
|
Cross-modal information maximization for medical imaging: Cmim
arXiv preprint arXiv:2010.10593, 2020 View on Google Scholar ↗ |
2020 | 6 | 25.9% |
|
Big Data: Theoretical Aspects [Scanning the Issue]
Proceedings of the IEEE 104 (1), 8-10, 2015 View on Google Scholar ↗ |
2015 | 9 | 25.7% |
|
Learning structural correspondences across different linguistic domains with synchronous neural language models
Proc. of the xLite Workshop on Cross-Lingual Technologies, NIPS, 2012 View on Google Scholar ↗ |
2012 | 9 | 25.6% |
|
Deep learning with denoising autoencoders
Journal of Machine Learning 27, 49-50, 2008 View on Google Scholar ↗ |
2008 | 8 | 25.5% |
|
Speeding up stochastic gradient descent
Neural Information Processing Systems Workshop on Efficient Machine Learning, 2007 View on Google Scholar ↗ |
2007 | 8 | 25.4% |
|
Forecasting and Trading Commodity Contract Spreads with Gaussian Processes
13th International Conference on Computing in Economics and Finance, 2007 View on Google Scholar ↗ |
2007 | 8 | 25.4% |
|
Long short-term memory
IEEE Trans. Neural Netw 5, 157-166, 1994 View on Google Scholar ↗ |
1994 | 7 | 25.4% |
|
Gradient-based learning for object detection, segmentation and recognition
Feature Grouping, 1999 View on Google Scholar ↗ |
1999 | 7 | 25.3% |
|
Probabilistic neural network models for sequential data
Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural …, 2000 View on Google Scholar ↗ |
2000 | 7 | 25.0% |
|
On the learning dynamics of deep neural networks
arXiv preprint arXiv:1809.06848, 2018 View on Google Scholar ↗ |
2018 | 7 | 24.6% |
|
Ieee transactions on neural networks
Input-output HMMs for sequence processing, 1231-1249, 1996 View on Google Scholar ↗ |
1996 | 6 | 24.5% |
|
Underwhelming generalization improvements from controlling feature attribution
View on Google Scholar ↗ |
2019 | 6 | 24.3% |
|
Learning deep architectures for AI, now foundations and trends
Now Publishers, Montreal, Canada, 2009 View on Google Scholar ↗ |
2009 | 7 | 24.2% |
|
Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv 2014
arXiv preprint arXiv:1412.3555, 2014 View on Google Scholar ↗ |
2014 | 8 | 24.1% |
|
Neural machine translation by jointly learning to align and translate. arXiv
arXiv preprint arXiv:1409.0473, 2014 View on Google Scholar ↗ |
2014 | 8 | 24.1% |
|
Aspects th eoriques de l'optimisation d'une r egle d'apprentissage
Actes de la conf erence Neuro-Nimes, 1992 View on Google Scholar ↗ |
1992 | 6 | 24.0% |
|
Use of multilayer networks for the recognition of phonetic features and phonemes
Computational intelligence 5 (2), 134-141, 1989 View on Google Scholar ↗ |
1989 | 6 | 23.9% |
|
A hybrid Pareto model for conditional density estimation of asymmetric fat-tail data
Artificial Intelligence and Statistics, 51-58, 2007 View on Google Scholar ↗ |
2007 | 7 | 23.7% |
|
Variance regularizing adversarial learning
arXiv preprint arXiv:1707.00309, 2017 View on Google Scholar ↗ |
2017 | 7 | 23.7% |
|
Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks
Cambridge: MIT Press, 1998 View on Google Scholar ↗ |
1998 | 6 | 23.7% |
|
Adaptive importance sampling to accelerate training of a neural probabilistic language model
Technical report, IDIAP, 2003 View on Google Scholar ↗ |
2003 | 6 | 23.3% |
|
Manifold parzen windows
Proc. NIPS, 825-832, 2003 View on Google Scholar ↗ |
2003 | 6 | 23.3% |
|
Adaptive importance sampling to accelerate training of a neural probabilistic language model
IDIAP, 2003 View on Google Scholar ↗ |
2003 | 6 | 23.3% |
|
Discussion of “the neural autoregressive distribution estimator”
Proceedings of the Fourteenth International Conference on Artificial …, 2011 View on Google Scholar ↗ |
2011 | 7 | 23.3% |
|
Deep learning on GPUs with Theano
The Learning Workshop, 2010 View on Google Scholar ↗ |
2010 | 7 | 23.1% |
|
Multi-task learning for option pricing
CIRANO, Centre interuniversitaire de recherche en analyse des organisations, 2002 View on Google Scholar ↗ |
2002 | 6 | 23.1% |
|
New distributed probabilistic language models. Dept. IRO, Université de Montréal, Montréal, QC
Canada, Tech. Rep 1215, 2002 View on Google Scholar ↗ |
2002 | 6 | 23.1% |
|
Segmentation en thèmes de conversations téléphoniques: traitement en amont pour l’extraction d’information
Actes de la 9ème conférence sur le Traitement Automatique des Langues …, 2002 View on Google Scholar ↗ |
2002 | 6 | 23.1% |
|
On out-of-sample statistics for time-series
CIRANO, 2002 View on Google Scholar ↗ |
2002 | 6 | 23.1% |
|
A Comparative Study of Learning Outcomes for Online Learning Platforms
International Conference on Artificial Intelligence in Education, 331-337, 2021 View on Google Scholar ↗ |
2021 | 4 | 22.9% |
|
Long-Term Credit Assignment via Model-based Temporal Shortcuts
Deep RL Workshop NeurIPS 2021, 2021 View on Google Scholar ↗ |
2021 | 4 | 22.9% |
|
Mastering rate based curriculum learning
arXiv preprint arXiv:2008.06456, 2020 View on Google Scholar ↗ |
2020 | 5 | 22.9% |
|
Joint learning of generative translator and classifier for visually similar classes
IEEE Access 8, 219160-219173, 2020 View on Google Scholar ↗ |
2020 | 5 | 22.9% |
|
Modeling cloud reflectance fields using conditional generative adversarial networks
arXiv preprint arXiv:2002.07579, 2020 View on Google Scholar ↗ |
2020 | 5 | 22.9% |
|
Numerical computation
Deep Learning, 78-95, 2016 View on Google Scholar ↗ |
2016 | 7 | 22.8% |
|
Locally weighted full covariance gaussian density estimation
Centre interuniversitaire de recherche en analyse des organisations (CIRANO), 2004 View on Google Scholar ↗ |
2004 | 6 | 22.8% |
|
Extending the framework of equilibrium propagation to general dynamics
View on Google Scholar ↗ |
2018 | 6 | 22.5% |
|
A dataset of topic-oriented human-to-chatbot dialogues
Tech. Rep., 2018.[Online]. Available: http://convai. io/2017/data …, 2018 View on Google Scholar ↗ |
2018 | 6 | 22.5% |
|
Brain tumor segmentation with deep neural networks
Proceedings MICCAI-BRATS, 01-05, 2014 View on Google Scholar ↗ |
2014 | 7 | 22.3% |
|
Efficient Causal Graph Discovery Using Large Language Models
arXiv preprint arXiv:2402.01207, 2024 View on Google Scholar ↗ |
2024 | 1 | 22.3% |
|
Ghost units yield biologically plausible backprop in deep neural networks
arXiv preprint arXiv:1911.08585, 2019 View on Google Scholar ↗ |
2019 | 5 | 21.7% |
|
The fascinating Facebook debate between Yann LeCun, Stuart Russel and Yoshua Bengio about the risks of strong AI
October, 2019 View on Google Scholar ↗ |
2019 | 5 | 21.7% |
|
On-line handwriting recognition with neural networks: Spatial representation versus temporal representation
Proceedings of the International Conference on Handwriting and Drawing, 1993 View on Google Scholar ↗ |
1993 | 5 | 21.6% |
|
Graph attention networks. CoRR
arXiv preprint arXiv:1710.10903, 2017 View on Google Scholar ↗ |
2017 | 6 | 21.6% |
|
On random weights for texture generation in one layer CNNS
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017 View on Google Scholar ↗ |
2017 | 6 | 21.6% |
|
An actor-critic algorithm for sequence prediction
Open Review. net. International Conference on Learning Representations, 1-17, 2017 View on Google Scholar ↗ |
2017 | 6 | 21.6% |
|
The statistical inefficiency of sparse coding for images (or, one Gabor to rule them all)
arXiv preprint arXiv:1109.6638, 2011 View on Google Scholar ↗ |
2011 | 6 | 21.5% |
|
A memory-efficient Huffman adaptive coding algorithm for very large sets of symbols
Université de Montréal, Rapport technique 1081, 1997 View on Google Scholar ↗ |
1997 | 5 | 21.0% |
|
Scaling large learning problems with hard parallel mixtures
International Workshop on Support Vector Machines, 8-23, 2002 View on Google Scholar ↗ |
2002 | 5 | 20.9% |
|
Adaptive Computation and Machine Learning Series
MIT Press, 2016 View on Google Scholar ↗ |
2016 | 6 | 20.8% |
|
Manifold parzen windows
Centre interuniversitaire de recherche en analyse des organisations (CIRANO), 2004 View on Google Scholar ↗ |
2004 | 5 | 20.7% |
|
Discovering shared structure in manifold learning
IRIS Machine Learning Workshop, 2004 View on Google Scholar ↗ |
2004 | 5 | 20.7% |
|
Trainable performance upper bounds for image and video captioning
arXiv preprint arXiv 1511, 2015 View on Google Scholar ↗ |
2015 | 6 | 20.6% |
|
Combining model-based and model-free RL via multi-step control variates
View on Google Scholar ↗ |
2018 | 5 | 20.2% |
|
Reinforced imitation learning from observations
View on Google Scholar ↗ |
2018 | 5 | 20.2% |
|
Learning deep architectures for AI. Foundations and Trends® in Machine Learning. 2009; 2 (1): 1–127
View on Google Scholar ↗ |
2009 | 5 | 20.1% |
|
Found. Trends Mach. Learn.
Found. Trends Mach. Learn 2 (1), 1, 2009 View on Google Scholar ↗ |
2009 | 5 | 20.1% |
|
Noisy K Best-Paths for Approximate Dynamic Programming with Application to Portfolio Optimization.
J. Comput. 2 (1), 12-19, 2007 View on Google Scholar ↗ |
2007 | 5 | 19.7% |
|
FedILC: Weighted Geometric Mean and Invariant Gradient Covariance for Federated Learning on Non-IID Data
arXiv preprint arXiv:2205.09305, 2022 View on Google Scholar ↗ |
2022 | 2 | 19.7% |
|
A General Purpose Neural Architecture for Geospatial Systems
arXiv preprint arXiv:2211.02348, 2022 View on Google Scholar ↗ |
2022 | 2 | 19.7% |
|
Bayesian Dynamic Causal Discovery
A causal view on dynamical systems, NeurIPS 2022 workshop, 2022 View on Google Scholar ↗ |
2022 | 2 | 19.7% |
|
Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One
arXiv preprint arXiv:2206.12840, 2022 View on Google Scholar ↗ |
2022 | 2 | 19.7% |
|
VIM: Variational Independent Modules for Video Prediction
Conference on Causal Learning and Reasoning, 70-89, 2022 View on Google Scholar ↗ |
2022 | 2 | 19.7% |
|
Diversifying Design of Nucleic Acid Aptamers Using Unsupervised Machine Learning
The Journal of Physical Chemistry B 127 (1), 62-68, 2022 View on Google Scholar ↗ |
2022 | 2 | 19.7% |
|
Spatially structured recurrent modules
International Conference on Learning Representations, 2020 View on Google Scholar ↗ |
2020 | 4 | 19.6% |
|
Constant Memory Attentive Neural Processes
arXiv preprint arXiv:2305.14567, 2023 View on Google Scholar ↗ |
2023 | 1 | 19.5% |
|
SatBird: a Dataset for Bird Species Distribution Modeling using Remote Sensing and Citizen Science Data
Thirty-seventh Conference on Neural Information Processing Systems Datasets …, 2023 View on Google Scholar ↗ |
2023 | 1 | 19.5% |
|
Pre-Training and Fine-Tuning Generative Flow Networks
arXiv preprint arXiv:2310.03419, 2023 View on Google Scholar ↗ |
2023 | 1 | 19.5% |
|
SatBird: Bird Species Distribution Modeling with Remote Sensing and Citizen Science Data
arXiv preprint arXiv:2311.00936, 2023 View on Google Scholar ↗ |
2023 | 1 | 19.5% |
|
Amortizing intractable inference in large language models
arXiv preprint arXiv:2310.04363, 2023 View on Google Scholar ↗ |
2023 | 1 | 19.5% |
|
Expected flow networks in stochastic environments and two-player zero-sum games
arXiv preprint arXiv:2310.02779, 2023 View on Google Scholar ↗ |
2023 | 1 | 19.5% |
|
DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets
Thirty-seventh Conference on Neural Information Processing Systems, 2023 View on Google Scholar ↗ |
2023 | 1 | 19.5% |
|
Batchgfn: Generative flow networks for batch active learning
arXiv preprint arXiv:2306.15058, 2023 View on Google Scholar ↗ |
2023 | 1 | 19.5% |
|
Towards equilibrium molecular conformation generation with GFlowNets
arXiv preprint arXiv:2310.14782, 2023 View on Google Scholar ↗ |
2023 | 1 | 19.5% |
|
Leveraging Diffusion Disentangled Representations to Mitigate Shortcuts in Underspecified Visual Tasks
arXiv preprint arXiv:2310.02230, 2023 View on Google Scholar ↗ |
2023 | 1 | 19.5% |
|
Crystal-GFN: sampling materials with desirable properties and constraints
AI for Accelerated Materials Design-NeurIPS 2023 Workshop, 2023 View on Google Scholar ↗ |
2023 | 1 | 19.5% |
|
A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems
arXiv preprint arXiv:2312.07511, 2023 View on Google Scholar ↗ |
2023 | 1 | 19.5% |
|
A community effort in SARS‐CoV‐2 drug discovery
Molecular Informatics, e202300262, 2023 View on Google Scholar ↗ |
2023 | 1 | 19.5% |
|
Let the flows tell: Solving graph combinatorial problems with GFlowNets
Thirty-seventh Conference on Neural Information Processing Systems, 2023 View on Google Scholar ↗ |
2023 | 1 | 19.5% |
|
Graph attention networks
Proceedings of the International Conference on Learning Representations …, 2017 View on Google Scholar ↗ |
2017 | 5 | 19.4% |
|
Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009; December 7-10, 2009, Vancouver, BC, Canada;[proceedings].
Curran, 2010 View on Google Scholar ↗ |
2010 | 5 | 19.3% |
|
The journey is the reward: Unsupervised learning of influential trajectories
arXiv preprint arXiv:1905.09334, 2019 View on Google Scholar ↗ |
2019 | 4 | 18.8% |
|
Learning powerful policies by using consistent dynamics model
arXiv preprint arXiv:1906.04355, 2019 View on Google Scholar ↗ |
2019 | 4 | 18.8% |
|
On random weights for texture generation in one layer neural networks
arXiv preprint arXiv:1612.06070, 2016 View on Google Scholar ↗ |
2016 | 5 | 18.6% |
|
Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models
arXiv preprint arXiv:2112.13734, 2021 View on Google Scholar ↗ |
2021 | 3 | 18.6% |
|
Cmim: Cross-modal information maximization for medical imaging
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 View on Google Scholar ↗ |
2021 | 3 | 18.6% |
|
From stdp towards biologically plausible deep learning
Deep Learning Workshop, International Conference on Machine Learning (ICML), 2015 View on Google Scholar ↗ |
2015 | 5 | 18.6% |
|
On the number of inference regions of deep feed forward networks with piece-wise linear activations. CoRR
View on Google Scholar ↗ |
2014 | 5 | 18.5% |
|
Proceedings of the 27th International Conference on Neural Information Processing Systems-Volume 2
View on Google Scholar ↗ |
2014 | 5 | 18.5% |
|
Extracting hidden sense probabilities from bitexts
Technical report, TR 1231, Departement d’informatique et recherche …, 2003 View on Google Scholar ↗ |
2003 | 4 | 18.5% |
|
Guest introduction: Special issue on new methods for model selection and model combination
Machine Learning 48 (1-3), 5-7, 2002 View on Google Scholar ↗ |
2002 | 4 | 18.3% |
|
Learning simple non-stationarities with hyper-parameters
submitted to Machine Learning, 1999 View on Google Scholar ↗ |
1999 | 4 | 18.2% |
|
Shared context probabilistic transducers
Advances in Neural Information Processing Systems 10, 1997 View on Google Scholar ↗ |
1997 | 4 | 18.1% |
|
Extended semantic tagging for entity extraction
Beyond Named Entity Recognition Semantic labeling for NLP tasks Workshop …, 2004 View on Google Scholar ↗ |
2004 | 4 | 18.1% |
|
Connectionist models and their application to automatic speech recognition
Machine Intelligence and Pattern Recognition 11, 175-194, 1991 View on Google Scholar ↗ |
1991 | 4 | 18.1% |
|
A comparative study on hybrid acoustic phonetic decoders based on artificial neural networks.
EUROSPEECH, 1991 View on Google Scholar ↗ |
1991 | 4 | 18.1% |
|
TrendsMach
Learn 2 (1), 1-127, 2009 View on Google Scholar ↗ |
2009 | 4 | 17.8% |
|
Tutorial: learning deep architectures
Videlectures. net videolectures. net/icml09_bengio_lecun_tldar, 2009 View on Google Scholar ↗ |
2009 | 4 | 17.8% |
|
Learning to rank for censored survival data
arXiv preprint arXiv:1806.01984, 2018 View on Google Scholar ↗ |
2018 | 4 | 17.5% |
|
Convolutional Neural Networks
View on Google Scholar ↗ |
2018 | 4 | 17.5% |
|
L'apprentissage profond
Massot éditions, 2018 View on Google Scholar ↗ |
2018 | 4 | 17.5% |
|
Towards open-text semantic parsing via multi-task learning of structured embeddings
arXiv preprint arXiv:1107.3663, 2011 View on Google Scholar ↗ |
2011 | 4 | 17.1% |
|
Contracting auto-encoders
Proceedings of the International Conference on Machine Learning (ICML …, 2011 View on Google Scholar ↗ |
2011 | 4 | 17.1% |
|
Deep self-taught learning for handwritten character recognition
NIPS* 2010 Deep Learning and Unsupervised Feature Learning Workshop, 2010 View on Google Scholar ↗ |
2010 | 4 | 16.9% |
|
Departement d’Informatique Et
Recherche Operationnelle (diro, Universite De Montreal, Lev Ratinov, and …, 2010 View on Google Scholar ↗ |
2010 | 4 | 16.9% |
|
Generative adversarial networks. arXiv
arXiv preprint arXiv:1406.2661, 2014 View on Google Scholar ↗ |
2014 | 4 | 16.3% |
|
Improving neural networks by preventing co-adaptation of feature detectors
Proc. 30th Conf. Artif. Intell.(AAAI 2016) 48 (1), 1-9, 2016 View on Google Scholar ↗ |
2016 | 4 | 16.3% |
|
Neural Bayes: A Generic Parameterization Method for Unsupervised Representation Learning
arXiv preprint arXiv:2002.09046, 2020 View on Google Scholar ↗ |
2020 | 3 | 16.2% |
|
Learning from learning machines: optimisation, rules, and social norms
arXiv preprint arXiv:2001.00006, 2019 View on Google Scholar ↗ |
2019 | 3 | 15.6% |
|
Distributed representation prediction for generalization to new words
Technical Report 1284, Université de Montréal, 2006. Département d …, 2006 View on Google Scholar ↗ |
2006 | 3 | 15.5% |
|
Generalizing to a zero-data task: a computational chemistry case study
Technical Report 1286, Département d’informatique et recherche …, 2006 View on Google Scholar ↗ |
2006 | 3 | 15.5% |
|
Semi-Supervised Learning
MIT Press, Cambridge, MA, 2006 View on Google Scholar ↗ |
2006 | 3 | 15.5% |
|
A hybrid Pareto model for asymmetric fat-tail data
Technical report 1283, Dept. IRO, Université de Montréal, 2006 View on Google Scholar ↗ |
2006 | 3 | 15.5% |
|
Stochastic learning of strategic equilibria for auctions
Neural computation 11 (5), 1199-1209, 1999 View on Google Scholar ↗ |
1999 | 3 | 15.4% |
|
Incorporating second-order functional knowledge for better option pricing
Centre interuniversitaire de recherche en analyse des organisations (CIRANO), 2002 View on Google Scholar ↗ |
2002 | 3 | 15.3% |
|
Estimation de densité conditionnelle lorsque l'hypothèse de normalité est insatisfaisante
Centre interuniversitaire de recherche en analyse des organisations (CIRANO), 2004 View on Google Scholar ↗ |
2004 | 3 | 15.3% |
|
Approche statistique pour le repérage de mots informatifs dans les textes oraux
Actes de la 11ème conférence sur le Traitement Automatique des Langues …, 2004 View on Google Scholar ↗ |
2004 | 3 | 15.3% |
|
Gaussian mixture densities for classification of nuclear power plant data
Computers and artificial intelligence 17, 189-210, 1998 View on Google Scholar ↗ |
1998 | 3 | 15.2% |
|
Learning deep architectures for AI, vol. 2, ch. 6–Greedy Layer-Wise Training of Deep Architecture
Now Publishers Inc, 2009 View on Google Scholar ↗ |
2009 | 3 | 15.1% |
|
Experiments on automatic speech recognition using BPS
Proc. International Joint Conference on Neural Networks, 1989 View on Google Scholar ↗ |
1989 | 3 | 14.8% |
|
{LeCun} Y, Lecun Y
Scaling Learning Algorithms towards AI. Large Scale Kernel Machines 1, 321-360, 2007 View on Google Scholar ↗ |
2007 | 3 | 14.7% |
|
Deep architectures for baby ai
View on Google Scholar ↗ |
2007 | 3 | 14.7% |
|
Low-memory convolutional neural networks through incremental depth-first processing
arXiv preprint arXiv:1804.10727, 2018 View on Google Scholar ↗ |
2018 | 3 | 14.6% |
|
A Walk with SGD: How SGD Explores Regions of Deep Network Loss?
View on Google Scholar ↗ |
2018 | 3 | 14.6% |
|
Iteratively unveiling new regions of interest in deep learning models
View on Google Scholar ↗ |
2018 | 3 | 14.6% |
|
A common GPU n-dimensional array for Python and C
Big Learning Workshop, NIPS, 2011 View on Google Scholar ↗ |
2011 | 3 | 14.4% |
|
Modeling natural image covariance with a spike and slab restricted Boltzmann machine
NIPS Workshop on Deep Learning, 2010 View on Google Scholar ↗ |
2010 | 3 | 14.4% |
|
Boundary-Seeking Generative Adversarial Networks
arXiv e-prints, arXiv: 1702.08431, 2017 View on Google Scholar ↗ |
2017 | 3 | 14.3% |
|
Joint training of deep boltzmann machines
arXiv preprint arXiv:1212.2686, 2012 View on Google Scholar ↗ |
2012 | 3 | 13.9% |
|
Exploring the wasserstein metric for time-to-event analysis
Survival Prediction-Algorithms, Challenges and Applications, 194-206, 2021 View on Google Scholar ↗ |
2021 | 2 | 13.8% |
|
Predicting unreliable predictions by shattering a neural network
View on Google Scholar ↗ |
2021 | 2 | 13.8% |
|
Training opposing directed models using geometric mean matching
CoRR, abs/1506.03877, 2015 View on Google Scholar ↗ |
2015 | 3 | 13.8% |
|
Denoising Criterion for Variational Auto-Encoding Framework
CoRR, vol. abs/1511.06406, 2015 View on Google Scholar ↗ |
2015 | 3 | 13.8% |
|
Backprop-free autoencoders
NIPS’2014 Deep Learning workshop, 2014 View on Google Scholar ↗ |
2014 | 3 | 13.6% |
|
The variational walkback algorithm
View on Google Scholar ↗ |
2016 | 3 | 13.6% |
|
Will Machines Eliminate Us?
TECHNOLOGY REVIEW 119 (2), 30-31, 2016 View on Google Scholar ↗ |
2016 | 3 | 13.6% |
|
Learning to deal with long-term dependencies
Neural Computation 9, 1735-1780, 1986 View on Google Scholar ↗ |
1986 | 2 | 12.3% |
|
Continual weight updates and convolutional architectures for equilibrium propagation
arXiv preprint arXiv:2005.04169, 2020 View on Google Scholar ↗ |
2020 | 2 | 12.1% |
|
COVI White Paper (preprint)
View on Google Scholar ↗ |
2020 | 2 | 12.1% |
|
Statistical and neural network models for speech recognition
Connectionist Approaches To Clinical Problems in Speech and Language …, 2001 View on Google Scholar ↗ |
2001 | 2 | 12.1% |
|
Pattern recognition and neural networks
Handbook of Brain Theory & Neural Networks, 1996 View on Google Scholar ↗ |
1996 | 2 | 12.0% |
|
NIPS-95 ORGANIZING COMMITTEE
Advances in Neural Information Processing Systems 8: Proceedings of the 1995 …, 1996 View on Google Scholar ↗ |
1996 | 2 | 12.0% |
|
Applying knowledge transfer for water body segmentation in Peru
arXiv preprint arXiv:1912.00957, 2019 View on Google Scholar ↗ |
2019 | 2 | 12.0% |
|
Predicting ice flow using machine learning
arXiv preprint arXiv:1910.08922, 2019 View on Google Scholar ↗ |
2019 | 2 | 12.0% |
|
Semi-Supervised Learning
Cambridge: MIT Press, 2006 View on Google Scholar ↗ |
2006 | 2 | 11.9% |
|
The K Best-Paths Approach to Approximate Dynamic Programming with Application to Portfolio Optimization
Advances in Artificial Intelligence: 19th Conference of the Canadian Society …, 2006 View on Google Scholar ↗ |
2006 | 2 | 11.9% |
|
Z-Coder: a fast adaptive binary arithmetic coder
US Patent App. 09/906,107, 2002 View on Google Scholar ↗ |
2002 | 2 | 11.8% |
|
The challenge of non-linear regression on large datasets with asymmetric heavy tails
Joint Stat. Meet. SPES 43, 193-205, 2002 View on Google Scholar ↗ |
2002 | 2 | 11.8% |
|
Kernel matching pursuit
Machine Learning 48, 165-187, 2002 View on Google Scholar ↗ |
2002 | 2 | 11.8% |
|
Metric-based model selection for time-series forecasting
Proceedings of the 12th IEEE Workshop on Neural Networks for Signal …, 2002 View on Google Scholar ↗ |
2002 | 2 | 11.8% |
|
Stochastic Gradient Descent on a Portfolio Management Training Criterion Using the IPA Gradient Estimator
Centre interuniversitaire de recherche en analyse des organisations (CIRANO), 2003 View on Google Scholar ↗ |
2003 | 2 | 11.8% |
|
Comment améliorer la capacité de généralisation des algorithmes d'apprentissage pour la prise de décisions financières
Centre interuniversitaire de recherche en analyse des organisations (CIRANO), 2003 View on Google Scholar ↗ |
2003 | 2 | 11.8% |
|
Learning deep hierarchies for AI
Foundations and Trends in Machine Learning 2 (1), 1-127, 2009 View on Google Scholar ↗ |
2009 | 2 | 11.6% |
|
On Out-of-Sample Statistics for Financial Time-Series
Rapport technique, Université de Montréal, 1999 View on Google Scholar ↗ |
1999 | 2 | 11.5% |
|
Memory-efficient adaptive Huffman coding.
Dr. Dobb's Journal: Software Tools for the Professional Programmer 23 (10 …, 1998 View on Google Scholar ↗ |
1998 | 2 | 11.5% |
|
AdaBoosting neural networks
Neural Comput., 967-972, 1997 View on Google Scholar ↗ |
1997 | 2 | 11.5% |
|
Analyses empiriques sur des transactions d’options
Technical Report 1176, Départment d’informatique et de Recherche …, 2000 View on Google Scholar ↗ |
2000 | 2 | 11.5% |
|
Linear Regression and the Optimization of Hyper-Parameters
Web Published Writings, 1-7, 2000 View on Google Scholar ↗ |
2000 | 2 | 11.5% |
|
Recurrent Neural Networks
View on Google Scholar ↗ |
1994 | 2 | 11.4% |
|
Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel
arXiv preprint arXiv:2205.10607, 2022 View on Google Scholar ↗ |
2022 | 1 | 11.3% |
|
Rethinking learning dynamics in rl using adversarial networks
View on Google Scholar ↗ |
2022 | 1 | 11.3% |
|
Graph-Based Active Machine Learning Method for Diverse and Novel Antimicrobial Peptides Generation and Selection
arXiv preprint arXiv:2209.13518, 2022 View on Google Scholar ↗ |
2022 | 1 | 11.3% |
|
Consistent Training via Energy-Based GFlowNets for Modeling Discrete Joint Distributions
arXiv preprint arXiv:2211.00568, 2022 View on Google Scholar ↗ |
2022 | 1 | 11.3% |
|
Neural attentive circuits
Advances in Neural Information Processing Systems 35, 7741-7754, 2022 View on Google Scholar ↗ |
2022 | 1 | 11.3% |
|
Convergence properties of deep neural networks on separable data
View on Google Scholar ↗ |
2018 | 2 | 11.3% |
|
FigureQA: An annotated figure dataset for visual reasoning
arXiv e-prints, arXiv: 1710.07300, 2017 View on Google Scholar ↗ |
2017 | 2 | 11.1% |
|
Training bidirectional Helmholtz machines
arXiv preprint arXiv:1506.03877, 2015 View on Google Scholar ↗ |
2015 | 2 | 10.6% |
|
Discrete-valued neural communication in structured architectures enhances generalization
View on Google Scholar ↗ |
2021 | 1 | 8.0% |
|
CAMAP: Artificial neural networks unveil the role of codon arrangement in modulating MHC-I peptides presentation
PLoS Computational Biology 17 (10), e1009482, 2021 View on Google Scholar ↗ |
2021 | 1 | 8.0% |
|
Divide and Explore: Multi-Agent Separate Exploration with Shared Intrinsic Motivations
View on Google Scholar ↗ |
2021 | 1 | 8.0% |
|
Automated curriculum generation for policy gradients from demonstrations
arXiv preprint arXiv:1912.00444, 2019 View on Google Scholar ↗ |
2019 | 1 | 7.2% |
|
InfoBot: Structured Exploration in ReinforcementLearning Using Information Bottleneck
View on Google Scholar ↗ |
2019 | 1 | 7.2% |
|
Avoidance learning using observational reinforcement learning
arXiv preprint arXiv:1909.11228, 2019 View on Google Scholar ↗ |
2019 | 1 | 7.2% |
|
Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
arXiv e-prints, arXiv: 2004.12485, 2020 View on Google Scholar ↗ |
2020 | 1 | 7.1% |
|
Graphmix: improved training of graph neural networks for semi-supervised learning
ArXiv, 2020 View on Google Scholar ↗ |
2020 | 1 | 7.1% |
|
Image-to-image Mapping with Many Domains by Sparse Attribute Transfer
arXiv preprint arXiv:2006.13291, 2020 View on Google Scholar ↗ |
2020 | 1 | 7.1% |
|
Training asynchronous input/output hidden markov models
AAAI Spring Symposium on Computational Issues in Learning Models of …, 1996 View on Google Scholar ↗ |
1996 | 1 | 6.9% |
|
Gaussian mixtures with missing data: an efficient EM training algorithm
Proceeding of the computing research association conference, Snowbird 155, 2008 View on Google Scholar ↗ |
2008 | 1 | 6.8% |
|
Discriminative Training of RBMs using Bhattacharyya Distance
Learning Workshop, Cliff Lodge, Snowbird, Utah, 2008 View on Google Scholar ↗ |
2008 | 1 | 6.8% |
|
Towards the latent transcriptome
arXiv preprint arXiv:1810.03442, 2018 View on Google Scholar ↗ |
2018 | 1 | 6.8% |
|
Disentangling Controllable and Uncontrollable Factors by Interacting with the World
Advances in Neural Information Processing Systems, 2018 View on Google Scholar ↗ |
2018 | 1 | 6.8% |
|
EnGAN: Latent Space MCMC and Maximum Entropy Generators for Energy-based Models
View on Google Scholar ↗ |
2018 | 1 | 6.8% |
|
Déclaration de Montréal pour un développement responsable de l'intelligence artificielle
https://www. declarationmontreal-iaresponsable. com/_files/ugd …, 2018 View on Google Scholar ↗ |
2018 | 1 | 6.8% |
|
Unsupervised one-to-many image translation
View on Google Scholar ↗ |
2018 | 1 | 6.8% |
|
Introduction to NIPS 2017 Competition Track
The NIPS'17 Competition: Building Intelligent Systems, 1-23, 2018 View on Google Scholar ↗ |
2018 | 1 | 6.8% |
|
Sgd smooths the sharpest directions
View on Google Scholar ↗ |
2018 | 1 | 6.8% |
|
Connectionist models applied to automatic speech recognition
McGill University, 1987 View on Google Scholar ↗ |
1987 | 1 | 6.7% |
|
An energy-based recurrent neural network for multiple fundamental frequency estimation
View on Google Scholar ↗ |
2011 | 1 | 6.7% |
|
A sense-smoothed bigram language model
Technical Report 1233, Dept. IRO, Universite de Montreal, 2003. 2, 4, 2003 View on Google Scholar ↗ |
2003 | 1 | 6.6% |
|
Brain tumor segmentation with deep neural networks
vol, 2017 View on Google Scholar ↗ |
2017 | 1 | 6.6% |
|
Image classification with complex cell neural networks
Front. Neurosci. Computational and Systems Neuroscience, 2010 View on Google Scholar ↗ |
2010 | 1 | 6.6% |
|
Stacked calibration of off-policy policy evaluation for video game matchmaking
2013 IEEE Conference on Computational Inteligence in Games (CIG), 1-8, 2013 View on Google Scholar ↗ |
2013 | 1 | 6.6% |
|
EmoNets: Multimodal deep learning approaches for emotion recognition in video
arXiv e-prints, arXiv: 1503.01800, 2015 View on Google Scholar ↗ |
2015 | 1 | 6.3% |
|
Show, Attend and Tell
Neural image caption generation with visual attention, 2015 View on Google Scholar ↗ |
2015 | 1 | 6.3% |
|
Denoising Criterion for Variational Auto-Encoding Framework
ArXiv e-prints, arXiv: 1511.06406, 2015 View on Google Scholar ↗ |
2015 | 1 | 6.3% |
|
32nd International Conference on Machine Learning, ICML 2015
JMLR. org, Lille, France, 2015 View on Google Scholar ↗ |
2015 | 1 | 6.3% |
|
Automatic detection of speech properties by the use of neural networks and human auditory system model.
Neural Networks 1, 289, 1988 View on Google Scholar ↗ |
1988 | 1 | 6.3% |
|
Empirical performance upper bounds for image and video captioning
View on Google Scholar ↗ |
2016 | 1 | 6.3% |
|
A hierarchical latent variable encoder-decoder model for generating dialogues
arXiv e-prints, arXiv: 1605.06069, 2016 View on Google Scholar ↗ |
2016 | 1 | 6.3% |
|
Task loss estimation for structured prediction
View on Google Scholar ↗ |
2016 | 1 | 6.3% |
|
Representation Learning
Technical report, 2012 View on Google Scholar ↗ |
2012 | 1 | 6.2% |
|
Joint training of partially-directed deep Boltzmann machines
NIPS Workshop on Deep Learning and Unsupervised Feature Learning, 1-10, 2012 View on Google Scholar ↗ |
2012 | 1 | 6.2% |
|
On the Use of an Ear Model and Multi-Layered Networks for Automatic Speech Recognition
Structural Pattern Analysis, 37-56, 1990 View on Google Scholar ↗ |
1990 | 1 | 6.1% |