Publications: Geoffrey Hinton
Download CSV for Geoffrey Hinton
| Title | Year | Citations | Score |
|---|---|---|---|
|
Deep learning
Nature 521 (7553), 436-44, 2015 View on Google Scholar ↗ |
2015 | 75703 | 100.0% |
|
Imagenet classification with deep convolutional neural networks
Advances in neural information processing systems 25, 2012 View on Google Scholar ↗ |
2012 | 149946 | 100.0% |
|
Visualizing data using t-SNE
Journal of Machine Learning Research 9 (Nov), 2579-2605, 2008 View on Google Scholar ↗ |
2008 | 41485 | 100.0% |
|
Reducing the dimensionality of data with neural networks
Science 313 (5786), 504-507, 2006 View on Google Scholar ↗ |
2006 | 22205 | 100.0% |
|
A fast learning algorithm for deep belief nets
Neural computation 18 (7), 1527-1554, 2006 View on Google Scholar ↗ |
2006 | 20913 | 100.0% |
|
Dropout: a simple way to prevent neural networks from overfitting
The journal of machine learning research 15 (1), 1929-1958, 2014 View on Google Scholar ↗ |
2014 | 48860 | 100.0% |
|
Rectified linear units improve restricted boltzmann machines
Proceedings of the 27th international conference on machine learning (ICML …, 2010 View on Google Scholar ↗ |
2010 | 24134 | 100.0% |
|
Learning multiple layers of features from tiny images
View on Google Scholar ↗ |
2009 | 27773 | 100.0% |
|
A simple framework for contrastive learning of visual representations
International conference on machine learning, 1597-1607, 2020 View on Google Scholar ↗ |
2020 | 15045 | 100.0% |
|
Distilling the knowledge in a neural network
arXiv preprint arXiv:1503.02531, 2015 View on Google Scholar ↗ |
2015 | 17985 | 100.0% |
|
Speech recognition with deep recurrent neural networks
2013 IEEE international conference on acoustics, speech and signal …, 2013 View on Google Scholar ↗ |
2013 | 11059 | 99.9% |
|
Learning representations by back-propagating errors
Nature 323 (6088), 533-536, 1986 View on Google Scholar ↗ |
1986 | 36977 | 99.9% |
|
Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups
IEEE Signal processing magazine 29 (6), 82-97, 2012 View on Google Scholar ↗ |
2012 | 13270 | 99.9% |
|
Learning internal representations by error-propagation
Parallel Distributed Processing: Explorations in the Microstructure of …, 1986 View on Google Scholar ↗ |
1986 | 32784 | 99.9% |
|
Improving neural networks by preventing co-adaptation of feature detectors
arXiv preprint arXiv:1207.0580, 2012 View on Google Scholar ↗ |
2012 | 10961 | 99.9% |
|
On the importance of initialization and momentum in deep learning
International conference on machine learning, 1139-1147, 2013 View on Google Scholar ↗ |
2013 | 5978 | 99.9% |
|
Layer normalization
arXiv preprint arXiv:1607.06450, 2016 View on Google Scholar ↗ |
2016 | 10489 | 99.9% |
|
Dynamic routing between capsules
Advances in neural information processing systems 30, 2017 View on Google Scholar ↗ |
2017 | 5499 | 99.8% |
|
Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude
Coursera: Neural networks for machine learning, 2012 View on Google Scholar ↗ |
2012 | 7585 | 99.8% |
|
International conference on machine learning
Transactions on machine learning research, 2023 View on Google Scholar ↗ |
2023 | 1282 | 99.8% |
|
A learning algorithm for Boltzmann machines
Cognitive science 9 (1), 147-169, 1985 View on Google Scholar ↗ |
1985 | 5585 | 99.8% |
|
Phoneme recognition using time-delay neural networks
Backpropagation, 35-61, 2013 View on Google Scholar ↗ |
2013 | 4142 | 99.8% |
|
Adaptive mixtures of local experts
Neural computation 3 (1), 79-87, 1991 View on Google Scholar ↗ |
1991 | 5748 | 99.8% |
|
Training products of experts by minimizing contrastive divergence
Neural computation 14 (8), 1771-1800, 2002 View on Google Scholar ↗ |
2002 | 6319 | 99.8% |
|
A practical guide to training restricted Boltzmann machines
View on Google Scholar ↗ |
2010 | 4184 | 99.7% |
|
Big self-supervised models are strong semi-supervised learners
Advances in neural information processing systems 33, 22243-22255, 2020 View on Google Scholar ↗ |
2020 | 2042 | 99.7% |
|
Deep Boltzmann machines
Artificial Intelligence and Statistics, 2009 View on Google Scholar ↗ |
2009 | 3877 | 99.7% |
|
When does label smoothing help?
Advances in neural information processing systems 32, 2019 View on Google Scholar ↗ |
2019 | 1885 | 99.7% |
|
Schemata and sequential thought processes in PDP models.
Parallel distributed processing: Explorations in the microstructure of …, 1986 View on Google Scholar ↗ |
1986 | 7238 | 99.6% |
|
Visualizing data using t-sne
Journal of machine learning research 9 (Nov), 2579-2605, 2008 View on Google Scholar ↗ |
2008 | 3468 | 99.6% |
|
The CIFAR-10 dataset
online: http://www. cs. toronto. edu/kriz/cifar. html 55 (5), 2014 View on Google Scholar ↗ |
2014 | 2398 | 99.5% |
|
A view of the EM algorithm that justifies incremental, sparse, and other variants
Learning in graphical models, 355-368, 1998 View on Google Scholar ↗ |
1998 | 3629 | 99.4% |
|
Neighbourhood components analysis
Advances in neural information processing systems 17, 2004 View on Google Scholar ↗ |
2004 | 2752 | 99.4% |
|
Restricted Boltzmann machines for collaborative filtering
Proceedings of the 24th international conference on Machine learning, 791-798, 2007 View on Google Scholar ↗ |
2007 | 2547 | 99.4% |
|
Acoustic modeling using deep belief networks
Audio, Speech, and Language Processing, IEEE Transactions on 20, 14-22, 2012 View on Google Scholar ↗ |
2012 | 2213 | 99.3% |
|
Connectionist learning procedures
Machine learning, 555-610, 1990 View on Google Scholar ↗ |
1990 | 2619 | 99.3% |
|
Outrageously large neural networks: The sparsely-gated mixture-of-experts layer
arXiv preprint arXiv:1701.06538, 2017 View on Google Scholar ↗ |
2017 | 1658 | 99.3% |
|
Improving deep neural networks for LVCSR using rectified linear units and dropout
2013 IEEE international conference on acoustics, speech and signal …, 2013 View on Google Scholar ↗ |
2013 | 1846 | 99.3% |
|
Generating text with recurrent neural networks
Proceedings of the 28th international conference on machine learning (ICML …, 2011 View on Google Scholar ↗ |
2011 | 1968 | 99.2% |
|
Neural networks for machine learning lecture 6a overview of mini-batch gradient descent
Cited on 14 (8), 2, 2012 View on Google Scholar ↗ |
2012 | 2020 | 99.2% |
|
Similarity of neural network representations revisited
International conference on machine learning, 3519-3529, 2019 View on Google Scholar ↗ |
2019 | 1023 | 99.2% |
|
New types of deep neural network learning for speech recognition and related applications: An overview
2013 IEEE international conference on acoustics, speech and signal …, 2013 View on Google Scholar ↗ |
2013 | 1558 | 99.1% |
|
Learning and relearning in Boltzmann machines
Parallel distributed processing: Explorations in the microstructure of …, 1986 View on Google Scholar ↗ |
1986 | 2323 | 99.0% |
|
Transforming auto-encoders
Artificial Neural Networks and Machine Learning–ICANN 2011: 21st …, 2011 View on Google Scholar ↗ |
2011 | 1664 | 99.0% |
|
Distributed representations
Parallel distributed processing: Explorations in the microstructure of …, 1986 View on Google Scholar ↗ |
1986 | 2182 | 99.0% |
|
Matrix capsules with EM routing
International conference on learning representations, 2018 View on Google Scholar ↗ |
2018 | 1135 | 99.0% |
|
Backpropagation and the brain
Nature Reviews Neuroscience 21 (6), 335-346, 2020 View on Google Scholar ↗ |
2020 | 726 | 98.9% |
|
Deep learning for AI
Communications of the ACM 64 (7), 58-65, 2021 View on Google Scholar ↗ |
2021 | 510 | 98.9% |
|
Autoencoders, minimum description length and Helmholtz free energy
Advances in neural information processing systems 6, 1993 View on Google Scholar ↗ |
1993 | 1818 | 98.9% |
|
Semantic hashing
SIGIR Workshop on Information Retrieval and Applications of Graphical Models …, 2007 View on Google Scholar ↗ |
2007 | 1723 | 98.9% |
|
Parallel models of associative memory
Lawrence Erlbaum Associates, 1981 View on Google Scholar ↗ |
1981 | 1639 | 98.8% |
|
Regularizing neural networks by penalizing confident output distributions
arXiv preprint arXiv:1701.06548, 2017 View on Google Scholar ↗ |
2017 | 1132 | 98.8% |
|
Simplifying neural networks by soft weight sharing
The Mathematics of Generalization, 373-394, 2018 View on Google Scholar ↗ |
2018 | 1029 | 98.8% |
|
How learning can guide evolution
Complex systems 1 (3), 495-502, 1987 View on Google Scholar ↗ |
1987 | 1671 | 98.8% |
|
Grammar as a foreign language
Advances in neural information processing systems 28, 2015 View on Google Scholar ↗ |
2015 | 1093 | 98.7% |
|
The helmholtz machine
Neural computation 7 (5), 889-904, 1995 View on Google Scholar ↗ |
1995 | 1660 | 98.7% |
|
Stochastic neighbor embedding
Advances in neural information processing systems 15, 2002 View on Google Scholar ↗ |
2002 | 1917 | 98.7% |
|
A general framework for parallel distributed processing
Parallel distributed processing: Explorations in the microstructure of …, 1986 View on Google Scholar ↗ |
1986 | 1658 | 98.7% |
|
Advances in neural information processing systems
Advances in neural information processing systems 32, 2019 View on Google Scholar ↗ |
2019 | 714 | 98.7% |
|
Learning multiple layers of representation
Trends in cognitive sciences 11 (10), 428-434, 2007 View on Google Scholar ↗ |
2007 | 1478 | 98.6% |
|
Lookahead optimizer: k steps forward, 1 step back
Advances in neural information processing systems 32, 2019 View on Google Scholar ↗ |
2019 | 679 | 98.6% |
|
The" wake-sleep" algorithm for unsupervised neural networks
Science 268 (5214), 1158-1161, 1995 View on Google Scholar ↗ |
1995 | 1518 | 98.6% |
|
Keeping the neural networks simple by minimizing the description length of the weights
Proceedings of the sixth annual conference on Computational learning theory …, 1993 View on Google Scholar ↗ |
1993 | 1445 | 98.5% |
|
Learning distributed representations of concepts
Proceedings of the eighth annual conference of the cognitive science society …, 1986 View on Google Scholar ↗ |
1986 | 1539 | 98.5% |
|
Zero-shot learning with semantic output codes
Advances in neural information processing systems 22, 2009 View on Google Scholar ↗ |
2009 | 1212 | 98.4% |
|
A scalable hierarchical distributed language model
Advances in neural information processing systems 21, 2008 View on Google Scholar ↗ |
2008 | 1278 | 98.4% |
|
Deep belief networks
Scholarpedia 4 (5), 5947, 2009 View on Google Scholar ↗ |
2009 | 1160 | 98.3% |
|
The appeal of parallel distributed processing
Parallel Distributed Processing: Explorations in the microstructure of …, 1986 View on Google Scholar ↗ |
1986 | 1331 | 98.3% |
|
A simple way to initialize recurrent networks of rectified linear units
arXiv preprint arXiv:1504.00941, 2015 View on Google Scholar ↗ |
2015 | 849 | 98.3% |
|
Neural additive models: Interpretable machine learning with neural nets
Advances in neural information processing systems 34, 4699-4711, 2021 View on Google Scholar ↗ |
2021 | 350 | 98.2% |
|
How to represent part-whole hierarchies in a neural network
Neural Computation 35 (3), 413-452, 2023 View on Google Scholar ↗ |
2023 | 170 | 98.2% |
|
Distilling a neural network into a soft decision tree
arXiv preprint arXiv:1711.09784, 2017 View on Google Scholar ↗ |
2017 | 683 | 97.8% |
|
Lesioning an attractor network: investigations of acquired dyslexia.
Psychological review 98 (1), 74, 1991 View on Google Scholar ↗ |
1991 | 1048 | 97.8% |
|
Modeling human motion using binary latent variables
Advances in neural information processing systems 19, 2006 View on Google Scholar ↗ |
2006 | 1002 | 97.7% |
|
Deep learning—a technology with the potential to transform health care
Jama 320 (11), 1101-1102, 2018 View on Google Scholar ↗ |
2018 | 596 | 97.6% |
|
A theoretical framework for back-propagation
Proceedings of the 1988 connectionist models summer school 1, 21-28, 1988 View on Google Scholar ↗ |
1988 | 1015 | 97.6% |
|
On rectified linear units for speech processing
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013 View on Google Scholar ↗ |
2013 | 723 | 97.5% |
|
On contrastive divergence learning
International workshop on artificial intelligence and statistics, 33-40, 2005 View on Google Scholar ↗ |
2005 | 995 | 97.5% |
|
Feudal reinforcement learning
Advances in neural information processing systems 5, 1992 View on Google Scholar ↗ |
1992 | 1032 | 97.5% |
|
Three new graphical models for statistical language modelling
Proceedings of the 24th international conference on Machine learning, 641-648, 2007 View on Google Scholar ↗ |
2007 | 947 | 97.4% |
|
Convolutional deep belief networks on cifar-10
Unpublished manuscript 40 (7), 1-9, 2010 View on Google Scholar ↗ |
2010 | 854 | 97.4% |
|
The EM algorithm for mixtures of factor analyzers
Technical Report CRG-TR-96-1, University of Toronto, 1996 View on Google Scholar ↗ |
1996 | 983 | 97.4% |
|
Boltzmann machines: Constraint satisfaction networks that learn
Carnegie-Mellon University, Department of Computer Science, 1984 View on Google Scholar ↗ |
1984 | 876 | 97.4% |
|
A time-delay neural network architecture for isolated word recognition
Neural networks 3 (1), 23-43, 1990 View on Google Scholar ↗ |
1990 | 915 | 97.2% |
|
Attend, infer, repeat: Fast scene understanding with generative models
Advances in neural information processing systems 29, 2016 View on Google Scholar ↗ |
2016 | 568 | 97.1% |
|
Optimal perceptual inference
Proceedings of the IEEE conference on Computer Vision and Pattern …, 1983 View on Google Scholar ↗ |
1983 | 855 | 97.0% |
|
Pix2seq: A language modeling framework for object detection
arXiv preprint arXiv:2109.10852, 2021 View on Google Scholar ↗ |
2021 | 228 | 97.0% |
|
Application of deep belief networks for natural language understanding
IEEE/ACM Transactions on Audio, Speech, and Language Processing 22 (4), 778-784, 2014 View on Google Scholar ↗ |
2014 | 569 | 96.9% |
|
Parallel distributed processing, Vols 1 and 2
Cambridge, MA: A Bradford Book, 1986 View on Google Scholar ↗ |
1986 | 823 | 96.9% |
|
Large scale distributed neural network training through online distillation
arXiv preprint arXiv:1804.03235, 2018 View on Google Scholar ↗ |
2018 | 457 | 96.7% |
|
Learning to detect roads in high-resolution aerial images
Computer Vision–ECCV 2010: 11th European Conference on Computer Vision …, 2010 View on Google Scholar ↗ |
2010 | 727 | 96.7% |
|
Unsupervised learning: foundations of neural computation
The MIT Press, 1999 View on Google Scholar ↗ |
1999 | 884 | 96.6% |
|
The forward-forward algorithm: Some preliminary investigations
arXiv preprint arXiv:2212.13345, 2022 View on Google Scholar ↗ |
2022 | 133 | 96.5% |
|
Replicated softmax: an undirected topic model
Advances in neural information processing systems 22, 2009 View on Google Scholar ↗ |
2009 | 666 | 96.4% |
|
Deep belief networks for phone recognition
Nips workshop on deep learning for speech recognition and related …, 2009 View on Google Scholar ↗ |
2009 | 646 | 96.3% |
|
Parameter estimation for linear dynamical systems
Technical Report CRG-TR-96-2, University of Totronto, Dept. of Computer Science, 1996 View on Google Scholar ↗ |
1996 | 759 | 96.3% |
|
Analog bits: Generating discrete data using diffusion models with self-conditioning
arXiv preprint arXiv:2208.04202, 2022 View on Google Scholar ↗ |
2022 | 121 | 96.1% |
|
Stacked capsule autoencoders
Advances in neural information processing systems 32, 2019 View on Google Scholar ↗ |
2019 | 300 | 96.0% |
|
How neural networks learn from experience
Scientific American 267 (3), 145-151, 1992 View on Google Scholar ↗ |
1992 | 709 | 96.0% |
|
Learning to combine foveal glimpses with a third-order Boltzmann machine
Advances in Neural Information Processing Systems 23 1, 2010 View on Google Scholar ↗ |
2010 | 602 | 95.9% |
|
Learning a nonlinear embedding by preserving class neighbourhood structure
Artificial intelligence and statistics, 412-419, 2007 View on Google Scholar ↗ |
2007 | 649 | 95.9% |
|
Using very deep autoencoders for content-based image retrieval.
ESANN 1, 2, 2011 View on Google Scholar ↗ |
2011 | 569 | 95.8% |
|
Vocal tract length perturbation (VTLP) improves speech recognition
Proc. ICML Workshop on Deep Learning for Audio, Speech and Language 117, 21, 2013 View on Google Scholar ↗ |
2013 | 487 | 95.8% |
|
Cvxnet: Learnable convex decomposition
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020 View on Google Scholar ↗ |
2020 | 238 | 95.6% |
|
Stochastic neighbor embedding
Advances in neural information processing systems 15, 857-864, 2003 View on Google Scholar ↗ |
2003 | 753 | 95.6% |
|
Self-organizing neural network that discovers surfaces in random-dot stereograms
Nature 355 (6356), 161-163, 1992 View on Google Scholar ↗ |
1992 | 664 | 95.6% |
|
Experiments on Learning by Back Propagation.
Technical Report CMU-CS-86-126, 1986 View on Google Scholar ↗ |
1986 | 605 | 95.6% |
|
Learning to label aerial images from noisy data
Proceedings of the 29th International conference on machine learning (ICML …, 2012 View on Google Scholar ↗ |
2012 | 493 | 95.6% |
|
Distilling the knowledge in a neural network. arXiv 2015
arXiv preprint arXiv:1503.02531 2, 2015 View on Google Scholar ↗ |
2015 | 418 | 95.5% |
|
Nasa neural articulated shape approximation
Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23 …, 2020 View on Google Scholar ↗ |
2020 | 234 | 95.5% |
|
The recurrent temporal restricted boltzmann machine
Advances in neural information processing systems 21, 2008 View on Google Scholar ↗ |
2008 | 593 | 95.4% |
|
Glove-talk: A neural network interface between a data-glove and a speech synthesizer
IEEE transactions on Neural Networks 4 (1), 2-8, 1993 View on Google Scholar ↗ |
1993 | 591 | 95.4% |
|
Classical and Bayesian inference in neuroimaging: theory
NeuroImage 16 (2), 465-483, 2002 View on Google Scholar ↗ |
2002 | 729 | 95.3% |
|
ImageNet classification with deep convolutional neural networks, Proceedings of the 25th International Conference on Neural Information Processing Systems
(NIPS'12) 1, 1097, 2012 View on Google Scholar ↗ |
2012 | 449 | 95.0% |
|
Parallel visual computation
Nature 306 (5938), 21-26, 1983 View on Google Scholar ↗ |
1983 | 508 | 94.8% |
|
Factored conditional restricted Boltzmann machines for modeling motion style
Proceedings of the 26th annual international conference on machine learning …, 2009 View on Google Scholar ↗ |
2009 | 505 | 94.8% |
|
Layer normalization. arXiv
arXiv preprint arXiv:1607.06450 10, 2016 View on Google Scholar ↗ |
2016 | 343 | 94.8% |
|
Exponential family harmoniums with an application to information retrieval
Advances in neural information processing systems 17, 2004 View on Google Scholar ↗ |
2004 | 605 | 94.7% |
|
Implementing semantic networks in parallel hardware
Parallel models of associative memory, 161-187, 1981 View on Google Scholar ↗ |
1981 | 461 | 94.6% |
|
A distributed connectionist production system
Cognitive science 12 (3), 423-466, 1988 View on Google Scholar ↗ |
1988 | 512 | 94.5% |
|
Binary coding of speech spectrograms using a deep auto-encoder
Eleventh annual conference of the international speech communication association, 2010 View on Google Scholar ↗ |
2010 | 476 | 94.5% |
|
Mapping part-whole hierarchies into connectionist networks
Artificial Intelligence 46 (1-2), 47-75, 1990 View on Google Scholar ↗ |
1990 | 472 | 94.2% |
|
Variational learning for switching state-space models
Neural computation 12 (4), 831-864, 2000 View on Google Scholar ↗ |
2000 | 605 | 94.0% |
|
Phone recognition with the mean-covariance restricted Boltzmann machine
Advances in neural information processing systems 23, 2010 View on Google Scholar ↗ |
2010 | 443 | 93.9% |
|
3D object recognition with deep belief nets
Advances in neural information processing systems 22, 2009 View on Google Scholar ↗ |
2009 | 445 | 93.8% |
|
A generalist framework for panoptic segmentation of images and videos
Proceedings of the IEEE/CVF International Conference on Computer Vision, 909-919, 2023 View on Google Scholar ↗ |
2023 | 55 | 93.8% |
|
Deep belief networks using discriminative features for phone recognition
2011 IEEE international conference on acoustics, speech and signal …, 2011 View on Google Scholar ↗ |
2011 | 405 | 93.8% |
|
Learning translation invariant recognition in a massively parallel networks
International conference on parallel architectures and languages Europe, 1-13, 1987 View on Google Scholar ↗ |
1987 | 413 | 93.7% |
|
Understanding how deep belief networks perform acoustic modelling
2012 IEEE international conference on acoustics, speech and signal …, 2012 View on Google Scholar ↗ |
2012 | 373 | 93.7% |
|
To recognize shapes, first learn to generate images
Computational Neuroscience: Theoretical Insights into Brain Function, 535-547, 2007 View on Google Scholar ↗ |
2007 | 462 | 93.7% |
|
Models of information processing in the brain
Parallel models of associative memory, 33-74, 2014 View on Google Scholar ↗ |
2014 | 321 | 93.6% |
|
Assessing the scalability of biologically-motivated deep learning algorithms and architectures
Advances in neural information processing systems 31, 2018 View on Google Scholar ↗ |
2018 | 254 | 93.6% |
|
A unified sequence interface for vision tasks
Advances in Neural Information Processing Systems 35, 31333-31346, 2022 View on Google Scholar ↗ |
2022 | 77 | 93.3% |
|
Modeling the manifolds of images of handwritten digits
IEEE transactions on Neural Networks 8 (1), 65-74, 1997 View on Google Scholar ↗ |
1997 | 483 | 93.3% |
|
Visualizing data using t-SNE
J. Mach. Learn. Res. 9 (Nov), 2579-2605, 2008 View on Google Scholar ↗ |
2008 | 425 | 93.2% |
|
Using fast weights to improve persistent contrastive divergence
Proceedings of the 26th annual international conference on machine learning …, 2009 View on Google Scholar ↗ |
2009 | 404 | 93.1% |
|
SMEM algorithm for mixture models
Neural computation 12 (9), 2109-2128, 2000 View on Google Scholar ↗ |
2000 | 525 | 93.0% |
|
Some demonstrations of the effects of structural descriptions in mental imagery
Cognitive Science 3 (3), 231-250, 1979 View on Google Scholar ↗ |
1979 | 354 | 92.8% |
|
An alternative model for mixtures of experts
Advances in neural information processing systems 7, 1994 View on Google Scholar ↗ |
1994 | 424 | 92.8% |
|
Using fast weights to attend to the recent past
Advances in neural information processing systems 29, 2016 View on Google Scholar ↗ |
2016 | 252 | 92.6% |
|
A parallel computation that assigns canonical object-based frames of reference
Proceedings of the 7th international joint conference on Artificial …, 1981 View on Google Scholar ↗ |
1981 | 329 | 92.4% |
|
Neuroanimator: Fast neural network emulation and control of physics-based models
Proceedings of the 25th annual conference on Computer graphics and …, 1998 View on Google Scholar ↗ |
1998 | 438 | 92.4% |
|
Who said what: Modeling individual labelers improves classification
Proceedings of the AAAI conference on artificial intelligence 32 (1), 2018 View on Google Scholar ↗ |
2018 | 218 | 92.3% |
|
Visualizing non-metric similarities in multiple maps
Machine learning 87, 33-55, 2012 View on Google Scholar ↗ |
2012 | 309 | 92.1% |
|
Using fast weights to deblur old memories
Proceedings of the ninth annual conference of the Cognitive Science Society …, 1987 View on Google Scholar ↗ |
1987 | 322 | 91.8% |
|
Massively parallel architectures for Al: NETL, Thistle, and Boltzmann machines
AAAI, 1983 View on Google Scholar ↗ |
1983 | 321 | 91.8% |
|
Learning to represent spatial transformations with factored higher-order Boltzmann machines
Neural computation 22 (6), 1473-1492, 2010 View on Google Scholar ↗ |
2010 | 318 | 91.0% |
|
Neurocomputing: Foundations of research
Cambridge, MA, USA: MIT Press, 1988 View on Google Scholar ↗ |
1988 | 321 | 90.9% |
|
Symbols among the neurons: Details of a connectionist inference architecture
IJCAI 85, 238-243, 1985 View on Google Scholar ↗ |
1985 | 306 | 90.7% |
|
On deep generative models with applications to recognition
CVPR 2011, 2857-2864, 2011 View on Google Scholar ↗ |
2011 | 286 | 90.7% |
|
Learning a better representation of speech soundwaves using restricted boltzmann machines
2011 IEEE International Conference on Acoustics, Speech and Signal …, 2011 View on Google Scholar ↗ |
2011 | 286 | 90.7% |
|
Parallel distributed processing: Explorations in the microstructure of cognition
View on Google Scholar ↗ |
1986 | 300 | 90.7% |
|
The development of the time-delay neural network architecture for speech recognition
Technical Report CMU-CS-88-152, 1988 View on Google Scholar ↗ |
1988 | 310 | 90.6% |
|
Deterministic Boltzmann learning performs steepest descent in weight-space
Neural computation 1 (1), 143-150, 1989 View on Google Scholar ↗ |
1989 | 295 | 90.5% |
|
Modeling pixel means and covariances using factorized third-order Boltzmann machines
2010 IEEE computer society conference on computer vision and pattern …, 2010 View on Google Scholar ↗ |
2010 | 302 | 90.5% |
|
Factored 3-way restricted boltzmann machines for modeling natural images
Proceedings of the thirteenth international conference on artificial …, 2010 View on Google Scholar ↗ |
2010 | 301 | 90.5% |
|
Robust and data-efficient generalization of self-supervised machine learning for diagnostic imaging
Nature Biomedical Engineering, 1-24, 2023 View on Google Scholar ↗ |
2023 | 36 | 90.5% |
|
Lecture 6a overview of mini–batch gradient descent
Coursera Lecture slides https://class. coursera. org/neuralnets-2012-001 …, 2012 View on Google Scholar ↗ |
2012 | 256 | 90.1% |
|
Imputer: Sequence modelling via imputation and dynamic programming
International Conference on Machine Learning, 1403-1413, 2020 View on Google Scholar ↗ |
2020 | 116 | 90.0% |
|
Learning representations by recirculation
Neural information processing systems, 1987 View on Google Scholar ↗ |
1987 | 267 | 90.0% |
|
Analyzing and improving representations with the soft nearest neighbor loss
International conference on machine learning, 2012-2020, 2019 View on Google Scholar ↗ |
2019 | 136 | 89.9% |
|
Generative models for discovering sparse distributed representations
Philosophical Transactions of the Royal Society of London. Series B …, 1997 View on Google Scholar ↗ |
1997 | 332 | 89.8% |
|
Connectionist architectures for artificial intelligence
IEEE Computer 20, 100-109, 1987 View on Google Scholar ↗ |
1987 | 260 | 89.6% |
|
Holography, associative memory, and inductive generalization
Parallel models of associative memory, 113-138, 2014 View on Google Scholar ↗ |
2014 | 212 | 89.5% |
|
Using deep belief nets to learn covariance kernels for Gaussian processes
Advances in neural information processing systems 20, 2007 View on Google Scholar ↗ |
2007 | 292 | 89.3% |
|
Divide the gradient by a running average of its recent magnitude. coursera: Neural networks for machine learning
Technical report, 2017 View on Google Scholar ↗ |
2017 | 171 | 89.2% |
|
Learning multilevel distributed representations for high-dimensional sequences
Artificial intelligence and statistics, 548-555, 2007 View on Google Scholar ↗ |
2007 | 289 | 89.2% |
|
Proceedings of the 27th international conference on machine learning (ICML-10)
Rectified linear units improve Restricted Boltzmann machines, 1-8, 2010 View on Google Scholar ↗ |
2010 | 268 | 89.1% |
|
Modeling documents with deep boltzmann machines
arXiv preprint arXiv:1309.6865, 2013 View on Google Scholar ↗ |
2013 | 222 | 89.1% |
|
Layer normalization (2016)
arXiv preprint arXiv:1607.06450, 1-14, 2016 View on Google Scholar ↗ |
2016 | 178 | 89.0% |
|
Robust and efficient medical imaging with self-supervision
arXiv preprint arXiv:2205.09723, 2022 View on Google Scholar ↗ |
2022 | 49 | 88.8% |
|
Frames of reference and mental imagery
Attention and performance IX, 261-277, 1981 View on Google Scholar ↗ |
1981 | 229 | 88.7% |
|
The CIFAR-10 dataset (2014)
Online: http://www. cs. toronto. edu/kriz/cifar. html 55, 2020 View on Google Scholar ↗ |
2020 | 102 | 88.5% |
|
Robust boltzmann machines for recognition and denoising
2012 IEEE conference on computer vision and pattern recognition, 2264-2271, 2012 View on Google Scholar ↗ |
2012 | 218 | 88.2% |
|
Phoneme recognition: neural networks vs. hidden markov models vs. hidden markov models
ICASSP-88., International Conference on Acoustics, Speech, and Signal …, 1988 View on Google Scholar ↗ |
1988 | 251 | 88.2% |
|
Global coordination of local linear models
Advances in neural information processing systems 14, 2001 View on Google Scholar ↗ |
2001 | 310 | 88.0% |
|
Learning sparse networks using targeted dropout
arXiv preprint arXiv:1905.13678, 2019 View on Google Scholar ↗ |
2019 | 113 | 87.6% |
|
Using generative models for handwritten digit recognition
IEEE transactions on pattern analysis and machine intelligence 18 (6), 592-606, 1996 View on Google Scholar ↗ |
1996 | 262 | 87.6% |
|
Unsupervised learning of image transformations
2007 IEEE Conference on Computer Vision and Pattern Recognition, 1-8, 2007 View on Google Scholar ↗ |
2007 | 253 | 87.5% |
|
Boltzmann machine
Scholarpedia 2 (5), 1668, 2007 View on Google Scholar ↗ |
2007 | 251 | 87.4% |
|
Using expectation-maximization for reinforcement learning
Neural Computation 9 (2), 271-278, 1997 View on Google Scholar ↗ |
1997 | 265 | 87.3% |
|
Preface to the special issue on connectionist symbol processing
Artificial Intelligence 46 (1-2), 1-4, 1990 View on Google Scholar ↗ |
1990 | 223 | 87.1% |
|
Canonical capsules: Self-supervised capsules in canonical pose
Advances in Neural information processing systems 34, 24993-25005, 2021 View on Google Scholar ↗ |
2021 | 65 | 86.7% |
|
A simple framework for contrastive learning of visual representations. arXiv 2020
arXiv preprint arXiv:2002.05709, 2020 View on Google Scholar ↗ |
2020 | 88 | 86.4% |
|
Neural Networks for Machine Learning, Lecture 15a
View on Google Scholar ↗ |
2019 | 103 | 86.4% |
|
Glove-TalkII-a neural-network interface which maps gestures to parallel formant speech synthesizer controls
IEEE transactions on neural networks 9 (1), 205-212, 1998 View on Google Scholar ↗ |
1998 | 250 | 86.2% |
|
TN Sainath, and B
Kingsbury,“Deep neural networks for acoustic modeling in speech recognition …, 2012 View on Google Scholar ↗ |
2012 | 184 | 85.8% |
|
Shape representation in parallel systems
Proceedings of the 7th international joint conference on Artificial …, 1981 View on Google Scholar ↗ |
1981 | 179 | 85.7% |
|
Deep belief nets for natural language call-routing
2011 IEEE International conference on acoustics, speech and signal …, 2011 View on Google Scholar ↗ |
2011 | 192 | 85.5% |
|
Parallel distributed processing
View on Google Scholar ↗ |
1986 | 185 | 85.4% |
|
A connectionist model of visual memory
Parallel Models of Associative Memory: Updated Edition, 65, 1981 View on Google Scholar ↗ |
1981 | 173 | 85.2% |
|
Learning sets of filters using back-propagation
Computer Speech & Language 2 (1), 35-61, 1987 View on Google Scholar ↗ |
1987 | 179 | 85.1% |
|
A better way to pretrain deep boltzmann machines
Advances in Neural Information Processing Systems 25, 2012 View on Google Scholar ↗ |
2012 | 175 | 85.0% |
|
Energy-based models for sparse overcomplete representations
Journal of Machine Learning Research 4 (Dec), 1235-1260, 2003 View on Google Scholar ↗ |
2003 | 248 | 85.0% |
|
Dynamical binary latent variable models for 3d human pose tracking
2010 IEEE Computer Society Conference on Computer Vision and Pattern …, 2010 View on Google Scholar ↗ |
2010 | 194 | 84.5% |
|
Reinforcement learning with factored states and actions
The Journal of Machine Learning Research 5, 1063-1088, 2004 View on Google Scholar ↗ |
2004 | 227 | 84.5% |
|
Analyzing cooperative computation
Proceedings of the fifth annual conference of the cognitive science society …, 1983 View on Google Scholar ↗ |
1983 | 162 | 84.3% |
|
Separating figure from ground with a parallel network
Perception 15 (2), 197-216, 1986 View on Google Scholar ↗ |
1986 | 168 | 84.2% |
|
Varieties of Helmholtz machine
Neural Networks 9 (8), 1385-1403, 1996 View on Google Scholar ↗ |
1996 | 201 | 84.1% |
|
Detecting and diagnosing adversarial images with class-conditional capsule reconstructions
arXiv preprint arXiv:1907.02957, 2019 View on Google Scholar ↗ |
2019 | 88 | 84.0% |
|
Learning symmetry groups with hidden units: Beyond the perceptron
Physica D: Nonlinear Phenomena 22 (1-3), 260-275, 1986 View on Google Scholar ↗ |
1986 | 165 | 83.9% |
|
Evaluation of adaptive mixtures of competing experts
Advances in neural information processing systems 3, 1990 View on Google Scholar ↗ |
1990 | 177 | 83.9% |
|
Adaptive elastic models for hand-printed character recognition
Advances in neural information processing systems 4, 1991 View on Google Scholar ↗ |
1991 | 179 | 83.9% |
|
Conditional Restricted Boltzmann Machines for Structured Output Prediction
Proc. Uncertainty in Artificial Intelligence, 2011 View on Google Scholar ↗ |
2011 | 173 | 83.9% |
|
Relaxation and its role in vision
University of Edinburgh, 1978 View on Google Scholar ↗ |
1978 | 141 | 83.8% |
|
Deep, narrow sigmoid belief networks are universal approximators
Neural computation 20 (11), 2629-2636, 2008 View on Google Scholar ↗ |
2008 | 188 | 83.6% |
|
Parallel distributed processing, volume 1: Explorations in the microstructure of cognition: Foundations
The MIT Press, 1986 View on Google Scholar ↗ |
1986 | 158 | 83.2% |
|
Rate-coded restricted Boltzmann machines for face recognition
Advances in neural information processing systems 13, 2000 View on Google Scholar ↗ |
2000 | 217 | 82.7% |
|
Unsupervised discovery of nonlinear structure using contrastive backpropagation
Cognitive science 30 (4), 725-731, 2006 View on Google Scholar ↗ |
2006 | 185 | 82.6% |
|
Parallel computations for controlling an arm
Journal of motor behavior 16 (2), 171-194, 1984 View on Google Scholar ↗ |
1984 | 140 | 82.4% |
|
Two Distributed-State Models For Generating High-Dimensional Time Series.
Journal of Machine Learning Research 12 (3), 2011 View on Google Scholar ↗ |
2011 | 158 | 82.4% |
|
Generating facial expressions with deep belief nets
Affective computing, emotion modelling, synthesis and recognition 2008 (5 …, 2008 View on Google Scholar ↗ |
2008 | 171 | 82.0% |
|
Neural networks: Tricks of the trade
Lect. Notes Comput. Sci 7700, 599-619, 2012 View on Google Scholar ↗ |
2012 | 144 | 81.8% |
|
Learning sparse topographic representations with products of student-t distributions
Advances in neural information processing systems 15, 2002 View on Google Scholar ↗ |
2002 | 197 | 81.6% |
|
Parallelizing neural networks during training
US Patent 9,811,775, 2017 View on Google Scholar ↗ |
2017 | 100 | 81.3% |
|
Managing ai risks in an era of rapid progress
arXiv preprint arXiv:2310.17688, 2023 View on Google Scholar ↗ |
2023 | 18 | 81.1% |
|
A new learning algorithm for mean field Boltzmann machines
International Conference on Artificial Neural Networks, 351-357, 2002 View on Google Scholar ↗ |
2002 | 188 | 80.9% |
|
Recognizing handwritten digits using mixtures of linear models
Advances in neural information processing systems 7, 1994 View on Google Scholar ↗ |
1994 | 156 | 80.9% |
|
Imagenet classification with deep convolutional neural networks
Advances in neural information processing systems 25, 1097-1105, 2012 View on Google Scholar ↗ |
2012 | 137 | 80.9% |
|
Representing part-whole hierarchies in connectionist networks
Proceedings of the Tenth Annual Conference of the Cognitive Science Society …, 1988 View on Google Scholar ↗ |
1988 | 146 | 80.5% |
|
Cifar-10 (canadian institute for advanced research). 2009
URL http://www. cs. toronto. edu/kriz/cifar. html 5, 2009 View on Google Scholar ↗ |
2009 | 151 | 80.3% |
|
Dynamic routing between capsules
Advances in neural information processing systems, 3856-3866, 2017 View on Google Scholar ↗ |
2017 | 95 | 80.3% |
|
Shape recognition and illusory conjunctions.
IJCAI, 252-259, 1985 View on Google Scholar ↗ |
1985 | 131 | 80.2% |
|
Discovering binary codes for documents by learning deep generative models
Topics in Cognitive Science 3 (1), 74-91, 2011 View on Google Scholar ↗ |
2011 | 139 | 80.2% |
|
Modeling image patches with a directed hierarchy of Markov random fields
Advances in neural information processing systems 20, 2007 View on Google Scholar ↗ |
2007 | 158 | 80.2% |
|
May. Speech recognition with deep recurrent neural networks
2013 IEEE international conference on acoustics, speech and signal …, 2013 View on Google Scholar ↗ |
2013 | 124 | 80.1% |
|
Scene-based and viewer-centered representations for comparing shapes
Cognition 30 (1), 1-35, 1988 View on Google Scholar ↗ |
1988 | 139 | 79.8% |
|
Simulating brain damage
Scientific American 268 (4), 76-82, 1993 View on Google Scholar ↗ |
1993 | 133 | 79.5% |
|
Gated softmax classification
Advances in neural information processing systems 23, 2010 View on Google Scholar ↗ |
2010 | 144 | 79.4% |
|
Learning to represent visual input
Philosophical Transactions of the Royal Society B: Biological Sciences 365 …, 2010 View on Google Scholar ↗ |
2010 | 142 | 79.2% |
|
Phone recognition using restricted boltzmann machines
2010 IEEE International Conference on Acoustics, Speech and Signal …, 2010 View on Google Scholar ↗ |
2010 | 142 | 79.2% |
|
2012 AlexNet
Adv. Neural Inf. Process. Syst, 1-9, 2012 View on Google Scholar ↗ |
2012 | 124 | 78.9% |
|
Where do features come from?
Cognitive science 38 (6), 1078-1101, 2014 View on Google Scholar ↗ |
2014 | 109 | 78.8% |
|
Proceedings of the 7th International Joint Conference on Artificial Intelligence
View on Google Scholar ↗ |
1981 | 107 | 78.5% |
|
Visualizing similarity data with a mixture of maps
Artificial intelligence and statistics, 67-74, 2007 View on Google Scholar ↗ |
2007 | 144 | 78.4% |
|
Matrix capsules with EM routing
6th international conference on learning representations, ICLR 115, 2018 View on Google Scholar ↗ |
2018 | 78 | 78.4% |
|
Unsupervised part representation by flow capsules
International Conference on Machine Learning, 9213-9223, 2021 View on Google Scholar ↗ |
2021 | 40 | 78.3% |
|
How learning can guide evolution
Adaptive individuals in evolving populations: models and algorithms 26, 447-454, 1996 View on Google Scholar ↗ |
1996 | 137 | 77.9% |
|
System and method for addressing overfitting in a neural network
US Patent 9,406,017, 2016 View on Google Scholar ↗ |
2016 | 89 | 77.5% |
|
Switching state-space models
Technical Report CRG-TR-96-3 DRAFT, Dept. of Computer Science, University of …, 1996 View on Google Scholar ↗ |
1996 | 133 | 77.4% |
|
A simple framework for contrastive learning of visual representations. preprint
arXiv preprint arXiv:2002.05709 1, 2020 View on Google Scholar ↗ |
2020 | 52 | 77.3% |
|
Does the wake-sleep algorithm produce good density estimators?
Advances in neural information processing systems 8, 1995 View on Google Scholar ↗ |
1995 | 127 | 77.3% |
|
Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. 2012
COURSERA: Neural Networks for Machine Learning, 2021 View on Google Scholar ↗ |
2021 | 38 | 77.3% |
|
Parallel models of associative memory
View on Google Scholar ↗ |
1981 | 100 | 77.2% |
|
Learning distributed representations of concepts using linear relational embedding
IEEE Transactions on Knowledge and Data Engineering 13 (2), 232-244, 2001 View on Google Scholar ↗ |
2001 | 146 | 76.6% |
|
Learning in graphical models
Dordrecht: Kluwer Academic Publishers, 355-368, 1998 View on Google Scholar ↗ |
1998 | 134 | 76.3% |
|
Topographic product models applied to natural scene statistics
Neural Computation 18 (2), 381-414, 2006 View on Google Scholar ↗ |
2006 | 130 | 76.1% |
|
The EM algorithm for factor analyzers
Technical Report CRG-TR-96-1, 1997 View on Google Scholar ↗ |
1997 | 127 | 75.7% |
|
Separating figure from ground with a Boltzmann machine
View on Google Scholar ↗ |
1987 | 100 | 75.6% |
|
Scaling forward gradient with local losses
arXiv preprint arXiv:2210.03310, 2022 View on Google Scholar ↗ |
2022 | 22 | 75.4% |
|
The toronto face database
Department of Computer Science, University of Toronto, Toronto, ON, Canada …, 2010 View on Google Scholar ↗ |
2010 | 114 | 74.9% |
|
Implicit mixtures of restricted Boltzmann machines
Advances in neural information processing systems 21, 2008 View on Google Scholar ↗ |
2008 | 117 | 74.8% |
|
Proceedings of the national conference on artificial intelligence
View on Google Scholar ↗ |
1983 | 85 | 74.5% |
|
Deep lambertian networks
arXiv preprint arXiv:1206.6445, 2012 View on Google Scholar ↗ |
2012 | 98 | 74.0% |
|
Introduction to the special section on deep learning for speech and language processing
IEEE Transactions on Audio, Speech, and Language Processing 20 (1), 4-6, 2011 View on Google Scholar ↗ |
2011 | 102 | 74.0% |
|
Developing population codes by minimizing description length
Advances in neural information processing systems 6, 1993 View on Google Scholar ↗ |
1993 | 96 | 73.5% |
|
A comparison of statistical learning methods on the GUSTO database
Statistics in medicine 17 (21), 2501-2508, 1998 View on Google Scholar ↗ |
1998 | 114 | 73.5% |
|
Glove-TalkII: an adaptive gesture-to-formant interface
Proceedings of the SIGCHI conference on Human factors in computing systems …, 1995 View on Google Scholar ↗ |
1995 | 101 | 73.0% |
|
Distilling theknowledge in a neural network
arXiv preprint arXiv:1503.02531 2 (7), 2015 View on Google Scholar ↗ |
2015 | 79 | 73.0% |
|
Generative versus discriminative training of RBMs for classification of fMRI images
Advances in neural information processing systems 21, 2008 View on Google Scholar ↗ |
2008 | 108 | 73.0% |
|
Generating more realistic images using gated mrf’s
NIPS 2858, 2859-2860, 2010 View on Google Scholar ↗ |
2010 | 104 | 73.0% |
|
The DELVE manual
URL http://www. cs. toronto. edu/~ delve, 1996 View on Google Scholar ↗ |
1996 | 103 | 72.6% |
|
A soft decision-directed LMS algorithm for blind equalization
IEEE Transactions on Communications 41 (2), 275-279, 1993 View on Google Scholar ↗ |
1993 | 91 | 72.6% |
|
Deep mixtures of factor analysers
arXiv preprint arXiv:1206.4635, 2012 View on Google Scholar ↗ |
2012 | 89 | 71.9% |
|
Deep learning
Nature 521 (7553), 436-444, 2015 View on Google Scholar ↗ |
2015 | 75 | 71.8% |
|
Layer normalization. CoRR abs/1607.06450 (2016)
arXiv preprint arXiv:1607.06450 178, 2016 View on Google Scholar ↗ |
2016 | 69 | 71.7% |
|
Subclass distillation
arXiv preprint arXiv:2002.03936, 2020 View on Google Scholar ↗ |
2020 | 40 | 71.4% |
|
Variational learning in nonlinear Gaussian belief networks
Neural Computation 11 (1), 193-213, 1999 View on Google Scholar ↗ |
1999 | 103 | 71.1% |
|
Split and merge EM algorithm for improving Gaussian mixture density estimates
Journal of VLSI signal processing systems for signal, image and video …, 2000 View on Google Scholar ↗ |
2000 | 113 | 71.1% |
|
A mobile robot that learns its place
Neural Computation 9 (3), 683-699, 1997 View on Google Scholar ↗ |
1997 | 98 | 70.8% |
|
ªA simple framework for contrastive learning of visual representations, º in
International conference on machine learning, 1597-1607, 2020 View on Google Scholar ↗ |
2020 | 39 | 70.8% |
|
Recognizing hand-written digits using hierarchical products of experts
Advances in neural information processing systems 13, 2000 View on Google Scholar ↗ |
2000 | 110 | 70.5% |
|
Illustrative language understanding: Large-scale visual grounding with image search
Proceedings of the 56th Annual Meeting of the Association for Computational …, 2018 View on Google Scholar ↗ |
2018 | 54 | 70.4% |
|
Darccc: Detecting adversaries by reconstruction from class conditional capsules
arXiv preprint arXiv:1811.06969, 2018 View on Google Scholar ↗ |
2018 | 54 | 70.4% |
|
Proceedings of the 24th international conference on Machine learning
ACM, 2007 View on Google Scholar ↗ |
2007 | 94 | 69.8% |
|
Distinguishing text from graphics in on-line handwritten ink
Ninth International Workshop on Frontiers in Handwriting Recognition, 142-147, 2004 View on Google Scholar ↗ |
2004 | 101 | 69.6% |
|
Modeling natural images using gated MRFs
IEEE transactions on pattern analysis and machine intelligence 35 (9), 2206-2222, 2013 View on Google Scholar ↗ |
2013 | 75 | 69.3% |
|
Learning multiple layers of features from tiny images. Vol. 1
vol 1, 7, 2009 View on Google Scholar ↗ |
2009 | 85 | 68.4% |
|
Building adaptive interface with neural networks: the glove-talk pilot study
Technical Report 90, 1990 View on Google Scholar ↗ |
1990 | 73 | 68.3% |
|
Inferring motor programs from images of handwritten digits
Advances in neural information processing systems 18, 2005 View on Google Scholar ↗ |
2005 | 89 | 67.9% |
|
Tensor analyzers
International conference on machine learning, 163-171, 2013 View on Google Scholar ↗ |
2013 | 70 | 67.7% |
|
What kind of graphical model is the brain?
IJCAI 5, 1765-1775, 2005 View on Google Scholar ↗ |
2005 | 87 | 67.5% |
|
2013 IEEE international conference on acoustics, speech and signal processing
IEEE, 2013 View on Google Scholar ↗ |
2013 | 69 | 67.3% |
|
Dynamic routing between capsules. arXiv
arXiv preprint arXiv:1710.09829, 2017 View on Google Scholar ↗ |
2017 | 53 | 67.1% |
|
Learning to parse images
Advances in neural information processing systems 12, 1999 View on Google Scholar ↗ |
1999 | 82 | 66.6% |
|
Mean field networks that learn to discriminate temporally distorted strings
Connectionist Models, 18-22, 1991 View on Google Scholar ↗ |
1991 | 66 | 66.5% |
|
GTM through time
IET Digital Library, 1997 View on Google Scholar ↗ |
1997 | 79 | 66.4% |
|
G‐maximization: an unsupervised learning procedure for discovering regularities
AIP conference proceedings 151 (1), 333-338, 1986 View on Google Scholar ↗ |
1986 | 59 | 66.2% |
|
The bootstrap Widrow-Hoff rule as a cluster-formation algorithm
Neural Computation 2 (3), 355-362, 1990 View on Google Scholar ↗ |
1990 | 65 | 65.9% |
|
Dropout: a simple way to prevent neural networks from overfitting
J. Mach. Learn. Res. 15, 1, 2014 View on Google Scholar ↗ |
2014 | 62 | 65.6% |
|
CIFAR-10
canadian institute for advanced research 5, 4, 2009 View on Google Scholar ↗ |
2009 | 73 | 65.0% |
|
Modeling the joint density of two images under a variety of transformations
CVPR 2011, 2793-2800, 2011 View on Google Scholar ↗ |
2011 | 69 | 65.0% |
|
others. 1988
Learning representations by back-propagating errors. Cognitive modeling 5 (3), 1, 1988 View on Google Scholar ↗ |
1988 | 62 | 64.8% |
|
Learning mixture models of spatial coherence
Neural Computation 5 (2), 267-277, 1993 View on Google Scholar ↗ |
1993 | 60 | 64.1% |
|
Nature
Nature 521 (7553), 436, 2015 View on Google Scholar ↗ |
2015 | 54 | 63.7% |
|
Distilling the knowledge in a neural network. CoRR abs/1503.02531 (2015)
arXiv preprint arXiv:1503.02531, 2015 View on Google Scholar ↗ |
2015 | 54 | 63.7% |
|
R. J. Williams;“
Learning Internal Representations by Error Propagation,” in Parallel …, 1986 View on Google Scholar ↗ |
1986 | 51 | 63.2% |
|
A desktop input device and interface for interactive 3d character animation
Graphics Interface 2, 133-140, 2002 View on Google Scholar ↗ |
2002 | 74 | 63.1% |
|
Deep Belief Nets.
Encyclopedia of Machine Learning, 267-269, 2010 View on Google Scholar ↗ |
2010 | 65 | 62.6% |
|
Adaptive soft weight tying using gaussian mixtures
Advances in Neural Information Processing Systems 4, 1991 View on Google Scholar ↗ |
1991 | 54 | 62.6% |
|
Teaching with commentaries
arXiv preprint arXiv:2011.03037, 2020 View on Google Scholar ↗ |
2020 | 28 | 62.4% |
|
Dimensionality reduction and prior knowledge in e-set recognition
Advances in neural information processing systems 2, 1989 View on Google Scholar ↗ |
1989 | 52 | 62.3% |
|
Discovering viewpoint-invariant relationships that characterize objects
Advances in neural information processing systems 3, 1990 View on Google Scholar ↗ |
1990 | 53 | 62.0% |
|
The Toronto face dataset
Technical Report UTML TR 2010-001, U. Toronto, 2010 View on Google Scholar ↗ |
2010 | 63 | 62.0% |
|
Speech recognition with deep recurrent neural networks (2013)
arXiv preprint arXiv:1303.5778, 2013 View on Google Scholar ↗ |
2013 | 54 | 61.3% |
|
Vinyals O Dean J Distilling the knowledge in a neural network Comput
Sci 14 (7), 38, 2015 View on Google Scholar ↗ |
2015 | 48 | 60.6% |
|
Lecture 6d-a separate, adaptive learning rate for each connection
Slides of lecture neural networks for machine learning 1, 1-31, 2012 View on Google Scholar ↗ |
2012 | 54 | 59.7% |
|
Some computational solutions to Bernstein's problems
Human Motor Actions—Bernstein Reassessed, 413-438, 1984 View on Google Scholar ↗ |
1984 | 41 | 59.7% |
|
Self supervised boosting
Advances in neural information processing systems 15, 2002 View on Google Scholar ↗ |
2002 | 62 | 59.6% |
|
Visualizing data using t-SNE
Journal of machine learning research 9, 2579-605, 2008 View on Google Scholar ↗ |
2008 | 59 | 59.5% |
|
Spatial Coherence as an Internal Teacher for a Neural Network
Backpropagation: theory, architectures, and applications, 313, 1995 View on Google Scholar ↗ |
1995 | 51 | 59.4% |
|
Temporal-kernel recurrent neural networks
Neural Networks 23 (2), 239-243, 2010 View on Google Scholar ↗ |
2010 | 56 | 59.2% |
|
A hierarchical community of experts
Learning in graphical models, 479-494, 1998 View on Google Scholar ↗ |
1998 | 55 | 59.2% |
|
Dark knowledge
Presented as the keynote in BayLearn 2 (2), 2014 View on Google Scholar ↗ |
2014 | 48 | 59.1% |
|
Parallel distributed processing: Explorations in the microstructure of cognition, vol. 1. chap. Learning Internal Representations by Error Propagation
MIT Press, Cambridge, MA, USA, 1986 View on Google Scholar ↗ |
1986 | 41 | 59.1% |
|
Learning sequential structure in simple recurrent networks
Parallel distributed processing: Experiments in the microstructure of …, 1986 View on Google Scholar ↗ |
1986 | 41 | 59.1% |
|
Solving random-dot stereograms using the heat equation
IEEE Computer Society Conference on Computer Vision and Pattern Recognition …, 1985 View on Google Scholar ↗ |
1985 | 43 | 59.0% |
|
International conference on machine learning
On the importance of initialization and momentum in deep learning, 1139-1147, 2013 View on Google Scholar ↗ |
2013 | 49 | 58.8% |
|
Why the islands move
Perception 13 (5), 629-632, 1984 View on Google Scholar ↗ |
1984 | 39 | 58.7% |
|
Evaluating the interface of a document processor: a comparison of expert judgement and user observation
Human-Computer Interaction-INTERACT 84, 1984 View on Google Scholar ↗ |
1984 | 39 | 58.7% |
|
A simple framework for contrastive learning of visual representations (2020)
arXiv preprint arXiv:2002.05709, 2002 View on Google Scholar ↗ |
2002 | 59 | 58.6% |
|
Comparing classification methods for longitudinal fMRI studies
Neural computation 22 (11), 2729-2762, 2010 View on Google Scholar ↗ |
2010 | 54 | 58.3% |
|
How to do backpropagation in a brain
Invited talk at the NIPS’2007 deep learning workshop 656, 1-16, 2007 View on Google Scholar ↗ |
2007 | 53 | 57.1% |
|
Visualizing data using t-SNE
J Mach Learn Res 9 (2605), 2579-2605, 2008 View on Google Scholar ↗ |
2008 | 52 | 56.7% |
|
TRAFFIC: Recognizing objects using hierarchical reference frame transformations
Advances in neural information processing systems 2, 1989 View on Google Scholar ↗ |
1989 | 39 | 56.6% |
|
Neighbourhood component analysis
Adv. Neural Inf. Process. Syst.(NIPS) 17 (513-520), 4, 2004 View on Google Scholar ↗ |
2004 | 54 | 56.5% |
|
Salakhutdinov
Improving neural networks by preventing co-adaptation of feature detectors …, 2012 View on Google Scholar ↗ |
2012 | 47 | 56.4% |
|
GEMINI: gradient estimation through matrix inversion after noise injection
Advances in neural information processing systems 1, 1988 View on Google Scholar ↗ |
1988 | 40 | 56.3% |
|
The relative accuracy of a variety of medical diagnostic programs
Methods of information in medicine 33 (04), 402-416, 1994 View on Google Scholar ↗ |
1994 | 44 | 56.2% |
|
Analysis-by-synthesis by learning to invert generative black boxes
Artificial Neural Networks-ICANN 2008: 18th International Conference, Prague …, 2008 View on Google Scholar ↗ |
2008 | 50 | 55.9% |
|
Gaussian-bernoulli rbms without tears
arXiv preprint arXiv:2210.10318, 2022 View on Google Scholar ↗ |
2022 | 10 | 55.7% |
|
Spiking boltzmann machines
Advances in neural information processing systems 12: proceedings of the …, 2000 View on Google Scholar ↗ |
2000 | 51 | 55.6% |
|
presented in part at the Proceedings of the 30th International Conference on International Conference on Machine Learning
Atlanta, GA, USA 28, 2013 View on Google Scholar ↗ |
2013 | 43 | 55.5% |
|
Products of hidden markov models
International Workshop on Artificial Intelligence and Statistics, 21-28, 2001 View on Google Scholar ↗ |
2001 | 48 | 55.0% |
|
Multiple relational embedding
Advances in neural information processing systems 17, 2004 View on Google Scholar ↗ |
2004 | 49 | 54.6% |
|
Wie neuronale Netze aus Erfahrung lernen
Spektrum der wissenschaft 11 (1992), 134-143, 1992 View on Google Scholar ↗ |
1992 | 37 | 53.9% |
|
Deflecting adversarial attacks
arXiv preprint arXiv:2002.07405, 2020 View on Google Scholar ↗ |
2020 | 20 | 53.6% |
|
An unsupervised learning procedure that discovers surfaces in random-dot stereograms
Proceedings of the International Joint Conference on Neural Networks 1, 218-222, 1990 View on Google Scholar ↗ |
1990 | 34 | 53.3% |
|
Discovering multiple constraints that are frequently approximately satisfied
arXiv preprint arXiv:1301.2278, 2013 View on Google Scholar ↗ |
2013 | 39 | 53.2% |
|
Using relaxation to find a puppet
Proc. of the AISB Summer Conference, 148-157, 1976 View on Google Scholar ↗ |
1976 | 27 | 52.8% |
|
Visualizing high-dimensional data using t-sne journal of machine learning research
J Mach Learn Res 9, 26, 2008 View on Google Scholar ↗ |
2008 | 43 | 52.6% |
|
System and method for labelling aerial images
US Patent 9,704,068, 2017 View on Google Scholar ↗ |
2017 | 30 | 52.5% |
|
Artificial intelligence and statistics
PMLR, 2009 View on Google Scholar ↗ |
2009 | 40 | 51.6% |
|
Distilling the knowledge in a neural network [EB/OL]
View on Google Scholar ↗ |
2015 | 33 | 51.0% |
|
Simclr: A simple framework for contrastive learning of visual representations
International Conference on Learning Representations 2, 4, 2020 View on Google Scholar ↗ |
2020 | 18 | 50.6% |
|
Hierarchical non-linear factor analysis and topographic maps
Advances in neural information processing systems 10, 1997 View on Google Scholar ↗ |
1997 | 35 | 50.3% |
|
Learning Generative Texture Models with extended Fields-of-Experts.
BMVC, 1-11, 2009 View on Google Scholar ↗ |
2009 | 37 | 50.0% |
|
Learning Multiple Layers of Features from Tiny Images. University of Toronto; Toronto, ON
Canada: 2009. Technical Report.[Google Scholar], 2009 View on Google Scholar ↗ |
2009 | 37 | 50.0% |
|
On the importance of momentum and initialization in deep learning
30th International Conference on Machine Learning, 404-439, 2013 View on Google Scholar ↗ |
2013 | 34 | 49.9% |
|
Using free energies to represent Q-values in a multiagent reinforcement learning task
Advances in Neural Information Processing Systems 13, 2000 View on Google Scholar ↗ |
2000 | 37 | 49.6% |
|
Evolution of artificial neural network architecture: prediction of depression after mania
Methods of information in medicine 37 (03), 220-225, 1998 View on Google Scholar ↗ |
1998 | 34 | 49.6% |
|
Parameter estimation for linear dynamical systems (Technical Report CRG-TR-96–2)
Toronto, ON: University of Toronto, Dept. of Computer Science, 1996 View on Google Scholar ↗ |
1996 | 30 | 49.1% |
|
Learning nonlinear constraints with contrastive backpropagation
Proceedings. 2005 IEEE International Joint Conference on Neural Networks …, 2005 View on Google Scholar ↗ |
2005 | 35 | 48.7% |
|
Imagery without arrays
Behavioral and Brain Sciences 2 (4), 555-556, 1979 View on Google Scholar ↗ |
1979 | 23 | 48.6% |
|
Deterministic Boltzmann learning in networks with asymmetric connectivity
Connectionist Models: Proceedings of the 1990 Summer School, 3-9, 1991 View on Google Scholar ↗ |
1991 | 27 | 48.5% |
|
Learning causally linked markov random fields
International Workshop on Artificial Intelligence and Statistics, 128-135, 2005 View on Google Scholar ↗ |
2005 | 34 | 48.2% |
|
Entering the black box of neural networks: a descriptive study of clinical variables predicting community-acquired pneumonia
Methods of information in medicine 42 (03), 287-296, 2003 View on Google Scholar ↗ |
2003 | 34 | 48.1% |
|
Efficient stochastic source coding and an application to a Bayesian network source model
The Computer Journal 40 (2_and_3), 157-165, 1997 View on Google Scholar ↗ |
1997 | 31 | 48.1% |
|
Rumelhart
Parallel and Distributed Processing, 1977 View on Google Scholar ↗ |
1977 | 21 | 48.0% |
|
Distilling the knowledge in a neural net-580 work
NIPS Deep Learning Workshop, 2014 View on Google Scholar ↗ |
2014 | 30 | 47.7% |
|
Local physical models for interactive character animation
Computer Graphics Forum 21 (3), 337-346, 2002 View on Google Scholar ↗ |
2002 | 33 | 47.6% |
|
A mode-hopping MCMC sampler
Technical Report CSRG-478, University of Toronto, submitted to Machine …, 2003 View on Google Scholar ↗ |
2003 | 33 | 47.6% |
|
Training distilled machine learning models
US Patent 10,289,962, 2019 View on Google Scholar ↗ |
2019 | 19 | 47.5% |
|
Free energy coding
Proceedings of Data Compression Conference-DCC'96, 73-81, 1996 View on Google Scholar ↗ |
1996 | 27 | 47.3% |
|
Parallel Distrilmted Processing
View on Google Scholar ↗ |
1986 | 22 | 47.2% |
|
Delve data sets
View on Google Scholar ↗ |
1996 | 26 | 46.6% |
|
Proceedings of the 1988 connectionist models summer school
Morgan Kaufman, 1989 View on Google Scholar ↗ |
1989 | 23 | 46.3% |
|
Guest editorial: Deep learning
International Journal of Computer Vision 113 (1), 1-2, 2015 View on Google Scholar ↗ |
2015 | 27 | 46.2% |
|
Coaching variables for regression and classification
Statistics and Computing 8, 25-33, 1998 View on Google Scholar ↗ |
1998 | 27 | 45.6% |
|
Improving a statistical language model through non-linear prediction
Neurocomputing 72 (7-9), 1414-1418, 2009 View on Google Scholar ↗ |
2009 | 29 | 45.4% |
|
Deep boltzmann machines
International Conference on Artificial Intelligence and Statistics, 448-455, 2009 View on Google Scholar ↗ |
2009 | 29 | 45.4% |
|
The ups and downs of Hebb synapses.
Canadian Psychology/Psychologie canadienne 44 (1), 10, 2003 View on Google Scholar ↗ |
2003 | 27 | 44.3% |
|
Using matrices to model symbolic relationship
Advances in neural information processing systems 21, 2008 View on Google Scholar ↗ |
2008 | 28 | 44.3% |
|
A simple algorithm that discovers efficient perceptual codes
Computational and Psychophysical Mechanisms of Visual Coding. Cambridge …, 1997 View on Google Scholar ↗ |
1997 | 24 | 43.8% |
|
System and method for parallelizing convolutional neural networks
US Patent 9,563,840, 2017 View on Google Scholar ↗ |
2017 | 21 | 43.8% |
|
Using an autoencoder with deformable templates to discover features for automated speech recognition.
INTERSPEECH, 1737-1740, 2013 View on Google Scholar ↗ |
2013 | 26 | 43.7% |
|
Learning hierarchical structures with linear relational embedding
Advances in neural information processing systems 14: proceedings of the …, 2002 View on Google Scholar ↗ |
2002 | 26 | 43.6% |
|
The role of spatial working memory in shape perception
Proceedings of the Third Cognitive Science Conference, 56-60, 1981 View on Google Scholar ↗ |
1981 | 17 | 43.5% |
|
Deep learning for speech recognition and related applications
NIPS workshop, 2009 View on Google Scholar ↗ |
2009 | 26 | 43.4% |
|
Using pairs of data-points to define splits for decision trees
Advances in Neural Information Processing Systems 8, 1995 View on Google Scholar ↗ |
1995 | 21 | 43.0% |
|
Computer-supported diagnosis of melanoma in profilometry
Methods of Information in Medicine 38 (01), 43-49, 1999 View on Google Scholar ↗ |
1999 | 24 | 43.0% |
|
An efficient learning procedure for deep Boltzmann machines
Neural Comput 24 (8), 1967-2006, 2012 View on Google Scholar ↗ |
2012 | 26 | 42.9% |
|
Lecture 6.5-rmsprop, coursera: Neural networks for machine learning
Coursera, video lectures, 307, 2012 View on Google Scholar ↗ |
2012 | 26 | 42.9% |
|
A new view of ICA
Proceedings of 3rd International Conference on Independent Component …, 2001 View on Google Scholar ↗ |
2001 | 24 | 42.8% |
|
Autoregressive product of multi-frame predictions can improve the accuracy of hybrid models
View on Google Scholar ↗ |
2014 | 24 | 42.7% |
|
Readings in cognitive science
California Univ San Diego La Jolla Inst for Cognitive Science, 399-421, 1988 View on Google Scholar ↗ |
1988 | 19 | 42.7% |
|
Canonical capsules: Unsupervised capsules in canonical pose
arXiv preprint arXiv:2012.04718 1, 2021 View on Google Scholar ↗ |
2021 | 10 | 42.5% |
|
Processing text using neural networks
US Patent 11,003,856, 2021 View on Google Scholar ↗ |
2021 | 10 | 42.5% |
|
Une nouvelle approche de la cognition: le connexionnisme
Le débat, 45-64, 1987 View on Google Scholar ↗ |
1987 | 18 | 42.4% |
|
Instantiating deformable models with a neural net
Computer vision and image understanding 68 (1), 120-126, 1997 View on Google Scholar ↗ |
1997 | 21 | 41.7% |
|
Machine learning for neuroscience
Neural systems & circuits 1 (1), 1-2, 2011 View on Google Scholar ↗ |
2011 | 24 | 41.6% |
|
PDP: Computational models of cognition and perception, I
I, chapter Learning internal representations by error propagation, 319-362, 1986 View on Google Scholar ↗ |
1986 | 16 | 41.4% |
|
Modeling pigeon behavior using a Conditional Restricted Boltzmann Machine.
ESANN, 2009 View on Google Scholar ↗ |
2009 | 23 | 41.1% |
|
System and method for generating training cases for image classification
US Patent 9,251,437, 2016 View on Google Scholar ↗ |
2016 | 20 | 40.7% |
|
Hand-printed digit recognition using deformable models
Spatial Vision in Humans and Robots, 1-23, 1993 View on Google Scholar ↗ |
1993 | 17 | 40.6% |
|
Proceedings of the Sixth Annual Conference on Computational Learning Theory. COLT’93
Association for Computing Machinery, New York, NY, USA, 1993 View on Google Scholar ↗ |
1993 | 17 | 40.6% |
|
Inferring the meaning of direct perception
Behavioral and Brain Sciences 3 (3), 387-388, 1980 View on Google Scholar ↗ |
1980 | 13 | 39.9% |
|
Glove-TalkII: Mapping hand gestures to speech using neural networks
Advances in neural information processing systems 7, 1994 View on Google Scholar ↗ |
1994 | 18 | 39.9% |
|
Wormholes improve contrastive divergence
Advances in Neural Information Processing Systems 16, 2003 View on Google Scholar ↗ |
2003 | 20 | 39.6% |
|
TRAFFIC: A model of object recognition based on transformations of feature instances
Proc. 1988 Connectionist Models Summer School, 452-461, 1988 View on Google Scholar ↗ |
1988 | 16 | 39.6% |
|
Learning Internal Representation by Error Propagation, Pararell Distributed Processing, Vol. 1
MIT Press, 1986 View on Google Scholar ↗ |
1986 | 14 | 39.3% |
|
Parallel Distributed Processing. Exploration of the Microstructure of Cognition. vol. 1: Foundations, DE Rumelhart and JL McClelland
MIT Press, 1986 View on Google Scholar ↗ |
1986 | 14 | 39.3% |
|
A better way to learn features: technical perspective
Communications of the ACM 54 (10), 94-94, 2011 View on Google Scholar ↗ |
2011 | 21 | 39.1% |
|
Using connectionist modules for decision support
Methods of Information in Medicine 29 (03), 167-181, 1990 View on Google Scholar ↗ |
1990 | 15 | 38.9% |
|
//Proc. Advances in Neural Inform.
Proces. Systems. 2012. V. 25. 25, 1090, 2012 View on Google Scholar ↗ |
2012 | 21 | 38.7% |
|
Computation by neural networks
nature neuroscience 3 (11), 1170-1170, 2000 View on Google Scholar ↗ |
2000 | 19 | 38.6% |
|
Phoneme recognition using time-delay neural networks (Technical Report TR-I-0006)
Japan: Advanced Telecommunications Research Institute, 1987 View on Google Scholar ↗ |
1987 | 14 | 38.6% |
|
The Helmholtz machine through time
ICANN-95, 483-490, 1995 View on Google Scholar ↗ |
1995 | 16 | 38.5% |
|
Visualizing data using t-SNE. journal of Machine Learning Research 9
Nov (2008), 2008 View on Google Scholar ↗ |
2008 | 20 | 38.3% |
|
Semantic hashing
International Journal of Approximate Reasoning 50 (7), 969-978, 2009 View on Google Scholar ↗ |
2009 | 19 | 38.1% |
|
Extracting distributed representations of concepts and relations from positive and negative propositions
Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural …, 2000 View on Google Scholar ↗ |
2000 | 18 | 37.8% |
|
Does the brain do inverse graphics
Brain and Cognitive Sciences Fall Colloquium 2, 2012 View on Google Scholar ↗ |
2012 | 20 | 37.8% |
|
Meta-Learning Fast Weight Language Models
arXiv preprint arXiv:2212.02475, 2022 View on Google Scholar ↗ |
2022 | 5 | 37.6% |
|
Connectionist models summer school
Proc. 1988 Connectionist Models Summer School, 1989 View on Google Scholar ↗ |
1989 | 14 | 37.5% |
|
Improving dimensionality reduction with spectral gradient descent
Neural networks 18 (5-6), 702-710, 2005 View on Google Scholar ↗ |
2005 | 18 | 37.4% |
|
Pattern matching and variable binding in a stochastic neural network
Genetic Algorithms and Simulated Annealing, 155-169, 1987 View on Google Scholar ↗ |
1987 | 13 | 37.3% |
|
A new way to learn acoustic events
Advances in Neural Information Processing Systems 24, 1-9, 2011 View on Google Scholar ↗ |
2011 | 18 | 36.4% |
|
Minimizing description length in an unsupervised neural network
Preprint, 1997 View on Google Scholar ↗ |
1997 | 15 | 36.2% |
|
Relaxing the hyperplane assumption in the analysis and modification of back-propagation neural networks
Cybernetics and Systems 9, 1711-1718, 1994 View on Google Scholar ↗ |
1994 | 14 | 35.9% |
|
DE Rumelhart and JL McClelland
Parallel Distributed Processing: Explorations in the Microstructure of Cognition, 1986 View on Google Scholar ↗ |
1986 | 11 | 35.5% |
|
Discovering high order features with mean field modules
Advances in neural information processing systems 2, 509-515, 1990 View on Google Scholar ↗ |
1990 | 12 | 35.2% |
|
Neurocomputing: Foundations of Research, Learning Representations by Back-Propagating Errors
MIT Press, Cambridge, MA, USA, 1988 View on Google Scholar ↗ |
1988 | 12 | 35.1% |
|
Neural network architectures for artificial intelligence
American Association for Artificial Intelligence, 1988 View on Google Scholar ↗ |
1988 | 12 | 35.1% |
|
Lookahead Optimizer: k steps forward, 1 step back. arXiv
arXiv preprint arXiv:1907.08610, 2019 View on Google Scholar ↗ |
2019 | 11 | 34.9% |
|
Visualizing data using t-sne journal of machine learning research
View on Google Scholar ↗ |
2008 | 16 | 34.9% |
|
Novice use of interactive graph-plotting system
IBM Hursley Human Factors Report# HF083. IBM UK Laboratories Ltd., Hursley …, 1983 View on Google Scholar ↗ |
1983 | 10 | 34.5% |
|
Acoustics, speech and signal processing (icassp), 2013 ieee international conference on
Speech recognition with deep recurrent neural networks, 6645-6649, 2013 View on Google Scholar ↗ |
2013 | 16 | 34.5% |
|
by Error Propagation
Readings in Machine Learning, 115, 1990 View on Google Scholar ↗ |
1990 | 11 | 33.7% |
|
The next generation of neural networks
Proceedings of the 43rd International ACM SIGIR Conference on Research and …, 2020 View on Google Scholar ↗ |
2020 | 9 | 33.7% |
|
Using a neural net to instantiate a deformable model
Advances in neural information processing systems 7, 1994 View on Google Scholar ↗ |
1994 | 12 | 33.4% |
|
Learning multiple layers of features from tiny images
Technical report, University of Toronto, 2009 View on Google Scholar ↗ |
2009 | 14 | 33.2% |
|
Learning to make coherent predictions in domains with discontinuities
Advances in Neural Information Processing Systems 4, 1991 View on Google Scholar ↗ |
1991 | 11 | 32.9% |
|
Training many small hidden markov models
WISP-2001 Workshop on Innovation in Speech Processing, Proc. Institute of …, 2001 View on Google Scholar ↗ |
2001 | 12 | 32.7% |
|
Representation and control in vision
Proceedings of the 1978 AISB/GI Conference on Artificial Intelligence, 309-314, 1978 View on Google Scholar ↗ |
1978 | 8 | 32.6% |
|
Systems and methods for contrastive learning of visual representations
US Patent 11,386,302, 2022 View on Google Scholar ↗ |
2022 | 4 | 32.5% |
|
Using mixtures of deformable models to capture variations in hand printed digits
Proceedings of the Third International Workshop on Frontiers in Handwriting …, 1993 View on Google Scholar ↗ |
1993 | 10 | 32.1% |
|
Visualizing data using t-SNE visualizing data using t-SNE
Journal of Machine Learning Research 9, 2579-2605, 2008 View on Google Scholar ↗ |
2008 | 13 | 31.8% |
|
Parameter estimation for linear dynamical systems University of Toronto technical report
CRG-TR-96-2, 1996 View on Google Scholar ↗ |
1996 | 10 | 31.8% |
|
Technical report
Technical Report CRG-TR-96-2. University of Totronto, Dept of Computer Science, 1996 View on Google Scholar ↗ |
1996 | 10 | 31.8% |
|
Parameter estimation for linear dynamical systems.(crg-tr-96-2)
University of Totronto. Dept. of Computer Science., Tech. Rep, 1996 View on Google Scholar ↗ |
1996 | 10 | 31.8% |
|
Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv
arXiv preprint arXiv:1207.0580, 2012 View on Google Scholar ↗ |
2012 | 14 | 31.7% |
|
Fast neural network emulation of dynamical systems for computer animation
Advances in neural information processing systems 11, 1998 View on Google Scholar ↗ |
1998 | 11 | 31.5% |
|
Probabilistic sequential independent components analysis
IEEE Transactions on Neural Networks 15 (4), 838-849, 2004 View on Google Scholar ↗ |
2004 | 12 | 31.4% |
|
Data for evaluating learning in valid experiments (delve)
Univ. Toronto, Toronto, ON, Canada, Tech. Rep 1, 2003 View on Google Scholar ↗ |
2003 | 11 | 31.1% |
|
Delve data for evaluating learning in valid experiments, 1995–1996
URL http://www. cs. toronto. edu/∼ delve, 2003 View on Google Scholar ↗ |
2003 | 11 | 31.1% |
|
Separation of HCM and LQT Cardiac Diseases with Machine Learning of Ca2+ Transient Profiles
Methods of Information in Medicine 58 (04/05), 167-178, 2019 View on Google Scholar ↗ |
2019 | 9 | 31.0% |
|
Neural networks for machine learning lecture 6a overview of mini-batch gradient descent
a lecture 14 (8), 2, 2012 View on Google Scholar ↗ |
2012 | 13 | 30.6% |
|
Products of hidden Markov models: It takes N> 1 to tango
arXiv preprint arXiv:1205.2614, 2012 View on Google Scholar ↗ |
2012 | 13 | 30.6% |
|
Imagenet
Adv. Neural Inf. Process. Syst. 25, 2012 View on Google Scholar ↗ |
2012 | 13 | 30.6% |
|
Neural networks for machine learning
Coursera, Video Lectures, Tech. Rep 264, 2012 View on Google Scholar ↗ |
2012 | 13 | 30.6% |
|
Proceedings of the 10th International Workshop on Artificial Intelligence and Statistics
Society for Artificial Intelligence and Statistics, 2005 View on Google Scholar ↗ |
2005 | 11 | 30.5% |
|
Abductive machine learning for modeling and predicting the educational score in school health surveys
Methods of information in medicine 35 (03), 265-271, 1996 View on Google Scholar ↗ |
1996 | 9 | 30.3% |
|
The EM algorithm for mixtures of factor analyzers (Tech. Rep. No. CRG-TR-96-1)
Toronto: University of Toronto, Department of Computer Science, 1997 View on Google Scholar ↗ |
1997 | 10 | 30.3% |
|
Learning in massively parallel nets
Proceedings of the Fifth AAAI National Conference on Artificial Intelligence …, 1986 View on Google Scholar ↗ |
1986 | 8 | 30.2% |
|
Unsupervised Learning: Foundations of Neural Computation (Computational Neuroscience)
MIT Press, 1999 View on Google Scholar ↗ |
1999 | 10 | 30.0% |
|
Potholes in the road to professionalism in medical informatics
Methods of information in medicine 34 (05), 434-440, 1995 View on Google Scholar ↗ |
1995 | 9 | 29.7% |
|
On contrastive divergence learning. 10th Int
Workshop on Artificial Intelligence and Statistics (AISTATS’2005), 2005 View on Google Scholar ↗ |
2005 | 10 | 29.3% |
|
Yee-Whye
A Fast Learning Algorithm for Deep Belief Nets, 1527-54, 2006 View on Google Scholar ↗ |
2006 | 10 | 29.0% |
|
Prediction of postoperative length of hospital stay based on differences in nursing narratives in elderly patients with epithelial ovarian cancer
Methods of Information in Medicine 58 (06), 222-228, 2019 View on Google Scholar ↗ |
2019 | 8 | 28.9% |
|
Stochastic neighbor embedding
Adv. Neural Inf. Process. Syst 15, 857-864, 2002 View on Google Scholar ↗ |
2002 | 9 | 28.2% |
|
Combining two methods of recognizing hand-printed digits
Art. Neural Systems 2, 53-60, 1992 View on Google Scholar ↗ |
1992 | 8 | 28.1% |
|
Learning and relearning in boltzman machines
Parallel Distributed Processing: Explorations in Microstructure of Cognition …, 1986 View on Google Scholar ↗ |
1986 | 7 | 28.0% |
|
Rectified linear units improve restricted boltzmann machines Proceedings of the 27th International Conference on International Conference on Machine Learning. 2010Last accesses on 2022 Jun 14 Madison, WI, USA Omnipress: 807–14 (ICML'10)
View on Google Scholar ↗ |
2010 | 10 | 27.5% |
|
Visualizing data using t-sne laurens van der maaten micc-ikat
J. Mach. Learn. Res 9, 2579-2605, 2017 View on Google Scholar ↗ |
2017 | 9 | 27.3% |
|
Gradient-based learning applied to document recognition
Commun. Acm 60, 84-90, 2017 View on Google Scholar ↗ |
2017 | 9 | 27.3% |
|
Deep belief networks
Scholarpedia 4 (5), 2009 View on Google Scholar ↗ |
2009 | 9 | 27.2% |
|
The EM algorithm for factor analyzers Technical Report CRG-TR-96-1
Toronto: University Of Toronto, 1997 View on Google Scholar ↗ |
1997 | 8 | 27.1% |
|
Visualizing Data using t-SNE Laurens van der Maaten
J. Mach. Learn. Res 1, 1-48, 2008 View on Google Scholar ↗ |
2008 | 9 | 27.0% |
|
Neural networks for computer-human interfaces: Glove-TalkII
Proceedings of the International Conference on Neural Information Processing …, 1996 View on Google Scholar ↗ |
1996 | 7 | 26.8% |
|
Matrix capsules with em routing
International conference on learning representations, 2018 View on Google Scholar ↗ |
2018 | 8 | 26.7% |
|
Learning Distributed Representations by Mapping Concepts and Relations into a Linear Space.
ICML, 711-718, 2000 View on Google Scholar ↗ |
2000 | 8 | 26.6% |
|
Modeling high-dimensional data by combining simple experts
AAAI/IAAI, 1159-1164, 2000 View on Google Scholar ↗ |
2000 | 8 | 26.6% |
|
Testing GLOM's ability to infer wholes from ambiguous parts
arXiv preprint arXiv:2211.16564, 2022 View on Google Scholar ↗ |
2022 | 3 | 26.5% |
|
El atractivo del procesamiento distribuido en paralelo
Rumelhart, DE; McClelland JL y el grupo PDP, 39-80, 1992 View on Google Scholar ↗ |
1992 | 7 | 26.2% |
|
Csc321: Introduction to neural networks and machine learning
Lecture 10, 2010 View on Google Scholar ↗ |
2010 | 9 | 26.1% |
|
Rmsprop gradient optimization (2014)
URL http://www. cs. toronto. edu/~ tijmen/csc321/slides/lecture_slides_lec6. pdf, 2020 View on Google Scholar ↗ |
2020 | 6 | 25.9% |
|
the PDP Research Group: Parallel Distributed Processing, 1
MIT Press, 1986 View on Google Scholar ↗ |
1986 | 6 | 25.8% |
|
Parallel distributed processing. Volume 1: Foundations
Cambridge, MA: MIT Press, 1986 View on Google Scholar ↗ |
1986 | 6 | 25.8% |
|
Aprendizagem Profunda
Nature 521 (7553), 436-444, 2015 View on Google Scholar ↗ |
2015 | 9 | 25.7% |
|
others,“Distilling the knowledge in a neural network,”
arXiv preprint arXiv:1503.02531 2 (7), 2015 View on Google Scholar ↗ |
2015 | 9 | 25.7% |
|
Neural Networks for Machine Learning, Lecture 6.5—RMSProp
Coursera.[(accessed on 26 January 2019)], 2012 View on Google Scholar ↗ |
2012 | 9 | 25.6% |
|
Relative density nets: a new way to combine backpropagation with hmm's
Advances in Neural Information Processing Systems 14, 2001 View on Google Scholar ↗ |
2001 | 7 | 25.4% |
|
The horizontal—vertical delusion
Perception 16 (5), 677-680, 1987 View on Google Scholar ↗ |
1987 | 6 | 25.3% |
|
Transforming auto-encoders
International conference on artificial neural networks, 44-51, 2011 View on Google Scholar ↗ |
2011 | 8 | 24.9% |
|
A quick learning calculation for profound conviction nets
Neural Computation 18 (7), 1527-1554, 2006 View on Google Scholar ↗ |
2006 | 7 | 24.5% |
|
andR. R. Salakhutdinov,“ReducingtheDimensionalityofDatawithNeuralNetG works”
Science 313, 5786, 2006 View on Google Scholar ↗ |
2006 | 7 | 24.5% |
|
Sejnowski
Cognitive Science 9, 147-169, 1985 View on Google Scholar ↗ |
1985 | 6 | 24.4% |
|
Cerberus: A multi-headed derenderer
arXiv preprint arXiv:1905.11940, 2019 View on Google Scholar ↗ |
2019 | 6 | 24.3% |
|
Mental simulation
Nature 347 (6294), 627-628, 1990 View on Google Scholar ↗ |
1990 | 6 | 24.2% |
|
Generative back-propagation
Abstracts 1st INNS, 1988 View on Google Scholar ↗ |
1988 | 6 | 24.1% |
|
Phoneme Recognition: Neural Networks vs. Hidden Markov Models Proc
IEEE International Conference on Acoustics, Speech and Signal Processing …, 1988 View on Google Scholar ↗ |
1988 | 6 | 24.1% |
|
Lecture 4a, Learning to predict the next word
Neural Networks for Machine Learning, Fall, 2015 View on Google Scholar ↗ |
2015 | 8 | 24.1% |
|
RMSProp adaptive learning
Coursera: Neural networks for machine learning, 2012 View on Google Scholar ↗ |
2012 | 8 | 24.1% |
|
Visualizing data using t-SNE
J. Mach. Learn. Res 9, 2579-2605, 2008 View on Google Scholar ↗ |
2008 | 7 | 23.9% |
|
User’s Guide for t-SNE Software
Structure, 2008 View on Google Scholar ↗ |
2008 | 7 | 23.9% |
|
Scaling in a hierarchical unsupervised network
IET Digital Library, 1999 View on Google Scholar ↗ |
1999 | 6 | 23.4% |
|
Parallel computation and the mass-spring model of motor control
Cognitive Science Laboratory, Center for Human Information Processing …, 1984 View on Google Scholar ↗ |
1984 | 5 | 23.3% |
|
Nonlinear dimensionality reduction using neural networks
RBM 2, 1000, 2000 View on Google Scholar ↗ |
2000 | 6 | 23.0% |
|
Layer normalization arxiv 1607.06450
Accessed, 2016 View on Google Scholar ↗ |
2016 | 7 | 22.8% |
|
Connectionist learning procedures (Tech. Rep. No. Computer Science Technical Report)
Pittsburgh, PA, 1987 View on Google Scholar ↗ |
1987 | 5 | 22.7% |
|
Lang K
Phoneme Recognition Using Time-Delay Neural Networks, 1987 View on Google Scholar ↗ |
1987 | 5 | 22.7% |
|
Taking inverse graphics seriously
View on Google Scholar ↗ |
2013 | 7 | 22.5% |
|
Deep learning. Nat. 521, 7553 (2015), 436–444
Crossref, ISI, 2015 View on Google Scholar ↗ |
2015 | 7 | 22.4% |
|
Greedy layer-wise algorithm
Journal of Machine Learning Research 1, 1-40, 2009 View on Google Scholar ↗ |
2009 | 6 | 22.3% |
|
Visualizing data using t-sne
Journal of Machine Learning Research 9 (2579-2605), 85, 2008 View on Google Scholar ↗ |
2008 | 6 | 22.0% |
|
Improving a statistical language model by modulating the effects of context words.
ESANN, 493-498, 2008 View on Google Scholar ↗ |
2008 | 6 | 22.0% |
|
Visualizing Data using t-SNE
View on Google Scholar ↗ |
2008 | 6 | 22.0% |
|
The deep learning revolution
Turing Lecture at FCRC, 2019 View on Google Scholar ↗ |
2019 | 5 | 21.7% |
|
Special Issue of Journal Artificial Intelligence on Connectionist Symbol Processing (edited by Hinton, GE)
Artificial Intelligence 46 (1-4), 1990 View on Google Scholar ↗ |
1990 | 5 | 21.6% |
|
TEH Y WA fast learning alforithm for deep beliefnets [J]
Momentum 9 (1), 1-20, 2010 View on Google Scholar ↗ |
2010 | 6 | 21.3% |
|
Respectively Reconsidered
Pragmatics Microfiche 3, 912-914, 1978 View on Google Scholar ↗ |
1978 | 4 | 21.3% |
|
Using spatial coherence as an internal teacher for a neural network
Advances in Back-Propagation, 1989 View on Google Scholar ↗ |
1989 | 5 | 21.2% |
|
Phoneme Recognition using Time-Delay Neural Network IEEE Trans
Vol. ASSP-37, 1989 View on Google Scholar ↗ |
1989 | 5 | 21.2% |
|
Cascaded redundancy reduction
Network: Computation in Neural Systems 9 (1), 73, 1998 View on Google Scholar ↗ |
1998 | 5 | 21.2% |
|
The EM algorithm for mixtures of factor analyzers Univ. Toronto, Toronto, ON
Canada, Tech. Rep. CRG-TR-96-1, 1997,(revised), 1997 View on Google Scholar ↗ |
1997 | 5 | 21.0% |
|
Lecture 6a overview of mini-batch gradient descent
View on Google Scholar ↗ |
2012 | 6 | 20.8% |
|
Training products of experts by minimizing contrastive divergence
Technical report, Brown University, 2012. 53, 143, 2012 View on Google Scholar ↗ |
2012 | 6 | 20.8% |
|
An efficient learning procedure for deep machines
Neural computation 24 (8), 1967-2006, 2012 View on Google Scholar ↗ |
2012 | 6 | 20.8% |
|
Deep Neural Networks for Acoustic Modeling
Speech Recognition IEEE Signal Processing Magazine, 2012 View on Google Scholar ↗ |
2012 | 6 | 20.8% |
|
Non-linear dimensionality reduction
University of Toronto Lecture Notes, 2013 View on Google Scholar ↗ |
2013 | 6 | 20.7% |
|
RMSprop Gradient Optimization
Lecture 6e of his Coursera Class, 2014 View on Google Scholar ↗ |
2014 | 6 | 20.5% |
|
Encyclopedia of machine learning and data mining
Springer, Boston, 2014 View on Google Scholar ↗ |
2014 | 6 | 20.5% |
|
Deep belief networks for phone recognition
NIPS 22 workshop on deep learning for speech recognition, 2009 View on Google Scholar ↗ |
2009 | 5 | 20.1% |
|
International Conference on Artificial Intelligence and Statistics
View on Google Scholar ↗ |
2009 | 5 | 20.1% |
|
Deep belief networks. Scholarpedia, 4, 5947
View on Google Scholar ↗ |
2009 | 5 | 20.1% |
|
Parallel stochastic search in early vision
Johns Hopkins University. Electrical Engineering and Computer Science Department, 1984 View on Google Scholar ↗ |
1984 | 4 | 19.9% |
|
Training distilled machine learning models
US Patent 11,423,337, 2022 View on Google Scholar ↗ |
2022 | 2 | 19.7% |
|
Systems and methods for contrastive learning of visual representations
US Patent 11,354,778, 2022 View on Google Scholar ↗ |
2022 | 2 | 19.7% |
|
Training distilled machine learning models
US Patent 10,650,328, 2020 View on Google Scholar ↗ |
2020 | 4 | 19.6% |
|
A simple framework for contrastive learning of visual representations. ICML
arXiv preprint arXiv:2002.05709, 2020 View on Google Scholar ↗ |
2020 | 4 | 19.6% |
|
Improving neural networks by preventing co-adaptation of feature detectors. arXiv: Neural and Evolutionary Computing
View on Google Scholar ↗ |
2012 | 5 | 18.8% |
|
Optimization: How to make the learning go faster
Coursera 4, 26-31, 2012 View on Google Scholar ↗ |
2012 | 5 | 18.8% |
|
Speech recog-nition with deep recurrent neural networks, ICASSP, 2013
Hannun, C. Case, J. Casper, B. Catanzaro, G. Diamos, E. Elsen, R. Prenger, S …, 2013 View on Google Scholar ↗ |
2013 | 5 | 18.7% |
|
Speech recognition with deep recurrent neural networks. IEEE Int. Conf. on Acoustics, Speech and Signal Processing
View on Google Scholar ↗ |
2013 | 5 | 18.7% |
|
GH-Nature, and U. 2015, Deep learning, vol. 521, no. 7553
Nature Publishing Group, 2015 View on Google Scholar ↗ |
2015 | 5 | 18.6% |
|
Embedding via clustering: using spectral information to guide dimensionality reduction
Proceedings. 2005 IEEE International Joint Conference on Neural Networks …, 2005 View on Google Scholar ↗ |
2005 | 4 | 18.4% |
|
GE (1992),“
How neural networks learn from experience”, Scientific American 267 (3), 144-151, 1992 View on Google Scholar ↗ |
1992 | 4 | 18.4% |
|
A Time-Delay Neural Network Architecture for Isolated Word Recognition
Artificial Neural Networks, Paradigms, Applications and Hardware, 1992 View on Google Scholar ↗ |
1992 | 4 | 18.4% |
|
Learning distributed representations of relational data using linear relational embedding
Neural Nets WIRN Vietri-01: Proceedings of the 12th Italian Workshop on …, 2002 View on Google Scholar ↗ |
2002 | 4 | 18.3% |
|
Switching state-space models (Technical Report)
Toronto, Canada, 1998 View on Google Scholar ↗ |
1998 | 4 | 18.2% |
|
Recent developments in deep learning
Lecture, The University of British Columbia, 2009 View on Google Scholar ↗ |
2009 | 4 | 17.8% |
|
Caching and replay of place sequences in a Temporal Restricted Boltzmann Machine model of the hippocampus
Cosyne (abstract only, Poster II-56), 2007 View on Google Scholar ↗ |
2007 | 4 | 17.3% |
|
University of Toronto
Technical Report, 2012 View on Google Scholar ↗ |
2012 | 4 | 16.6% |
|
Lecture 6.5-rmsprop
COURSERA: Neural networks for machine learning, 2012 View on Google Scholar ↗ |
2012 | 4 | 16.6% |
|
Grammar as a foreign language
Advances in Neural Information Processing Systems, 2015 View on Google Scholar ↗ |
2015 | 4 | 16.3% |
|
System and method for parallelizing convolutional neural networks
US Patent 10,635,966, 2020 View on Google Scholar ↗ |
2020 | 3 | 16.2% |
|
System and method for addressing overfitting in a neural network
US Patent 10,366,329, 2019 View on Google Scholar ↗ |
2019 | 3 | 15.6% |
|
Pattern classification using a mixture of factor analyzers
Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE …, 1999 View on Google Scholar ↗ |
1999 | 3 | 15.4% |
|
15 Learning to Use Spike Timing in a Restricted Boltzmann Machine
Probabilistic Models of the Brain, 285, 2002 View on Google Scholar ↗ |
2002 | 3 | 15.3% |
|
Morgan-Kaufmann
Los Altos CA, 1990 View on Google Scholar ↗ |
1990 | 3 | 15.2% |
|
Phoneme recognition: neural networks vs hidden markov models
ATR Interpreting Telephony Research Laboratories, 07-110, 1988 View on Google Scholar ↗ |
1988 | 3 | 15.2% |
|
Simplifying Neural Networks by Soft Weight Sharing
SANTA FE INSTITUTE STUDIES IN THE SCIENCES OF COMPLEXITY-PROCEEDINGS VOLUME …, 1994 View on Google Scholar ↗ |
1994 | 3 | 15.1% |
|
The unity of consciousness: A connectionist account
Memories, Thoughts, and Emotions: Essays in Honor of George Mandler, 245, 1991 View on Google Scholar ↗ |
1991 | 3 | 14.9% |
|
Journal of Machine Learning Research 9
View on Google Scholar ↗ |
2008 | 3 | 14.8% |
|
Considerations in dynamic time warping algorithms for discrete word recognition
IEEE Transactions on Acoustics, Speech and Signal Processing 37 (3), 328-339, 1989 View on Google Scholar ↗ |
1989 | 3 | 14.8% |
|
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
View on Google Scholar ↗ |
2010 | 3 | 14.4% |
|
Fast inference and learning for modeling documents with a deep boltzmann machine
View on Google Scholar ↗ |
2013 | 3 | 14.0% |
|
Coursera: Neural networks for machine learning-Lecture 6.5: RMSprop
University of Toronto, Toronto, ON, Canada, 2012 View on Google Scholar ↗ |
2012 | 3 | 13.9% |
|
Rmsprop: Divide the gradient by a running average of its recent magnitude. Coursera
Neural Networks for Machine Learning, 31, 2012 View on Google Scholar ↗ |
2012 | 3 | 13.9% |
|
Guest editorial: Deep learning
International Journal of Computer Vision 113 (1), 1-2, 2015 View on Google Scholar ↗ |
2015 | 3 | 13.8% |
|
Parallel Distributed Emergence
Parallel Distributed Processing: Explorations in the Microstructure of …, 1986 View on Google Scholar ↗ |
1986 | 2 | 12.3% |
|
Learning Internal Representations by Error Propagation. DE Rumelhart and J. McClelland, editors, Parallel Distributed Processing
The MIT Press, Cambridge, MA, 1986 View on Google Scholar ↗ |
1986 | 2 | 12.3% |
|
Recurrent neural networks with rectified linear units
US Patent 10,635,972, 2020 View on Google Scholar ↗ |
2020 | 2 | 12.1% |
|
Using neural networks to monitor for rare failures
MECHANICAL WORKING AND STEEL PROCESSING CONFERENCE PROCEEDINGS, 545-548, 1996 View on Google Scholar ↗ |
1996 | 2 | 12.0% |
|
Modelling the statistics of natural images with topographic product of student-t models
Neural Computation 18 (2), 2006 View on Google Scholar ↗ |
2006 | 2 | 11.9% |
|
Models of human inference
Computational intelligence 3 (3), 189-190, 1987 View on Google Scholar ↗ |
1987 | 2 | 11.8% |
|
Neural networks for pattern recognition. Advanced texts in econometrics
Clarendon Press, 1995 View on Google Scholar ↗ |
1995 | 2 | 11.8% |
|
Developing population codes for object instantiation parameters
AAAI Fall Symposium Series: Machine Learning in Computer Vision Raleigh …, 1993 View on Google Scholar ↗ |
1993 | 2 | 11.7% |
|
A comparison of classification methods for longitudinal fmri studies
Neuroimage 47, S57, 2009 View on Google Scholar ↗ |
2009 | 2 | 11.6% |
|
Using mixtures of factor analyzers for segmentation and pose estimation
Unpublished, 1998 View on Google Scholar ↗ |
1998 | 2 | 11.5% |
|
E cient stochastic source coding and an application to a Bayesian network source model
Computer Journal 4, 1997 View on Google Scholar ↗ |
1997 | 2 | 11.5% |
|
Capsule neural networks
US Patent 11,494,609, 2022 View on Google Scholar ↗ |
2022 | 1 | 11.3% |
|
Convex representation of objects using neural network
US Patent 11,508,167, 2022 View on Google Scholar ↗ |
2022 | 1 | 11.3% |
|
Restricted boltzmann machines.”
View on Google Scholar ↗ |
2013 | 2 | 10.9% |
|
Attend, infer, repeat: Fast scene understanding with generative models
Advances in, 2016 View on Google Scholar ↗ |
2016 | 2 | 10.6% |
|
System and method for addressing overfitting in a neural network
US Patent 10,977,557, 2021 View on Google Scholar ↗ |
2021 | 1 | 8.0% |
|
Technical Report CMU-Cs 84-119
Carnegie Mellon University, Pittsburgh, PA, 1984 View on Google Scholar ↗ |
1984 | 1 | 7.7% |
|
Scaling RBMs to High Dimensional Data with Invertible Neural Networks
ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit …, 2020 View on Google Scholar ↗ |
2020 | 1 | 7.1% |
|
Artificial Intelligence: Neural Networks
Van Nostrand's Scientific Encyclopedia, 2005 View on Google Scholar ↗ |
2005 | 1 | 7.0% |
|
Deep Generative Models for Modeling Animate Motion
Proc. 4th Int. Symp. Adaptive Motion of Animals and Machines, 2008 View on Google Scholar ↗ |
2008 | 1 | 6.8% |
|
Learning and Evaluaing Deep Bolztmann Machines
View on Google Scholar ↗ |
2008 | 1 | 6.8% |
|
Preface to “Simplifying Neural Networks by Soft Weight Sharing”
The Mathematics Of Generalization, 369-371, 2018 View on Google Scholar ↗ |
2018 | 1 | 6.8% |
|
Learning fast neural network emulators for physics-based models
ACM SIGGRAPH 97 Visual Proceedings: The art and interdisciplinary programs …, 1997 View on Google Scholar ↗ |
1997 | 1 | 6.7% |
|
Technical Perspective A Better Way to Learn Features
Communications of the ACM 54 (10), 2011 View on Google Scholar ↗ |
2011 | 1 | 6.7% |
|
Using neural networks to learn intractable generative models
Annual Meeting of the American Statistical Association, 1994 View on Google Scholar ↗ |
1994 | 1 | 6.6% |
|
SCENE-BASED AND VIEWER-CENTERED REPRESENTATIONS FOR COMPARING SHAPE
BULLETIN OF THE PSYCHONOMIC SOCIETY 26 (6), 510-510, 1988 View on Google Scholar ↗ |
1988 | 1 | 6.3% |