Geoffrey E. Hinton

Geoffrey Hinton received his BA in Experimental Psychology from Cambridge in 1970 and his PhD in Artificial Intelligence from Edinburgh in 1978. He did postdoctoral work at Sussex University and the University of California San Diego and spent five years as a faculty member in the Computer Science department at Carnegie-Mellon University. He then became a fellow of the Canadian Institute for Advanced Research and moved to the Department of Computer Science at the University of Toronto. He spent three years from 1998 until 2001 setting up the Gatsby Computational Neuroscience Unit at University College London and then returned to the University of Toronto where he is now an emeritus distinguished professor. From 2004 until 2013 he was the director of the program on "Neural Computation and Adaptive Perception" which is funded by the Canadian Institute for Advanced Research. Since 2013 he has been working half-time for Google in Mountain View and Toronto.

Geoffrey Hinton is a fellow of the Royal Society, the Royal Society of Canada, and the Association for the Advancement of Artificial Intelligence. He is an honorary foreign member of the American Academy of Arts and Sciences and the National Academy of Engineering, and a former president of the Cognitive Science Society. He has received honorary doctorates from the University of Edinburgh, the University of Sussex, and the University of Sherbrooke. He was awarded the first David E. Rumelhart prize (2001), the IJCAI award for research excellence (2005), the Killam prize for Engineering (2012) , The IEEE James Clerk Maxwell Gold medal (2016), and the NSERC Herzberg Gold Medal (2010) which is Canada's top award in Science and Engineering.

Geoffrey Hinton designs machine learning algorithms. His aim is to discover a learning procedure that is efficient at finding complex structure in large, high-dimensional datasets and to show that this is how the brain learns to see. He was one of the researchers who introduced the back-propagation algorithm and the first to use backpropagation for learning word embeddings. His other contributions to neural network research include Boltzmann machines, distributed representations, time-delay neural nets, mixtures of experts, variational learning, products of experts and deep belief nets. His research group in Toronto made major breakthroughs in deep learning that have revolutionized speech recognition and object classification.

Google Publications

Previous Publications

  •  

    Guest Editorial: Deep Learning

    Marc'Aurelio Ranzato, Geoffrey E. Hinton, Yann LeCun

    International Journal of Computer Vision, vol. 113 (2015), pp. 1-2

  •  

    Application of Deep Belief Networks for Natural Language Understanding

    Ruhi Sarikaya, Geoffrey E. Hinton, Anoop Deoras

    IEEE/ACM Trans. Audio, Speech & Language Processing, vol. 22 (2014), pp. 778-784

  •  

    Dropout: a simple way to prevent neural networks from overfitting

    Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov

    Journal of Machine Learning Research, vol. 15 (2014), pp. 1929-1958

  •  

    Where Do Features Come From?

    Geoffrey Hinton

    Cognitive Science, vol. 38 (2014), pp. 1078-1101

  •  

    Discovering Multiple Constraints that are Frequently Approximately Satisfied

    Geoffrey E. Hinton, Yee Whye Teh

    CoRR, vol. abs/1301.2278 (2013)

  •  

    Improving deep neural networks for LVCSR using rectified linear units and dropout

    George E. Dahl, Tara N. Sainath, Geoffrey E. Hinton

    ICASSP (2013), pp. 8609-8613

  •  

    Modeling Documents with Deep Boltzmann Machines

    Nitish Srivastava, Ruslan Salakhutdinov, Geoffrey E. Hinton

    CoRR, vol. abs/1309.6865 (2013)

  •  

    Modeling Documents with Deep Boltzmann Machines

    Nitish Srivastava, Ruslan Salakhutdinov, Geoffrey E. Hinton

    UAI (2013)

  •  

    Modeling Natural Images Using Gated MRFs

    Marc'Aurelio Ranzato, Volodymyr Mnih, Joshua M. Susskind, Geoffrey E. Hinton

    IEEE Trans. Pattern Anal. Mach. Intell., vol. 35 (2013), pp. 2206-2222

  •  

    New types of deep neural network learning for speech recognition and related applications: an overview

    Li Deng, Geoffrey E. Hinton, Brian Kingsbury

    ICASSP (2013), pp. 8599-8603

  •  

    On the importance of initialization and momentum in deep learning

    Ilya Sutskever, James Martens, George E. Dahl, Geoffrey E. Hinton

    ICML (3) (2013), pp. 1139-1147

  •  

    Speech Recognition with Deep Recurrent Neural Networks

    Alex Graves, Abdel-rahman Mohamed, Geoffrey E. Hinton

    CoRR, vol. abs/1303.5778 (2013)

  •  

    Speech recognition with deep recurrent neural networks

    Alex Graves, Abdel-rahman Mohamed, Geoffrey E. Hinton

    ICASSP (2013), pp. 6645-6649

  •  

    Tensor Analyzers

    Yichuan Tang, Ruslan Salakhutdinov, Geoffrey E. Hinton

    ICML (3) (2013), pp. 163-171

  •  

    Using an autoencoder with deformable templates to discover features for automated speech recognition

    Navdeep Jaitly, Geoffrey E. Hinton

    INTERSPEECH (2013), pp. 1737-1740

  •  

    A Better Way to Pretrain Deep Boltzmann Machines

    Ruslan Salakhutdinov, Geoffrey E. Hinton

    NIPS (2012), pp. 2456-2464

  •  

    A Practical Guide to Training Restricted Boltzmann Machines

    Geoffrey E. Hinton

    Neural Networks: Tricks of the Trade (2nd ed.) (2012), pp. 599-619

  •  

    Acoustic Modeling Using Deep Belief Networks

    Abdel-rahman Mohamed, George E. Dahl, Geoffrey E. Hinton

    IEEE Trans. Audio, Speech & Language Processing, vol. 20 (2012), pp. 14-22

  •  

    An Efficient Learning Procedure for Deep Boltzmann Machines

    Ruslan Salakhutdinov, Geoffrey E. Hinton

    Neural Computation, vol. 24 (2012), pp. 1967-2006

  •  

    Conditional Restricted Boltzmann Machines for Structured Output Prediction

    Volodymyr Mnih, Hugo Larochelle, Geoffrey E. Hinton

    CoRR, vol. abs/1202.3748 (2012)

  •  

    Deep Lambertian Networks

    Yichuan Tang, Ruslan Salakhutdinov, Geoffrey E. Hinton

    ICML (2012)

  •  

    Deep Mixtures of Factor Analysers

    Yichuan Tang, Ruslan Salakhutdinov, Geoffrey E. Hinton

    CoRR, vol. abs/1206.4635 (2012)

  •  

    Deep Mixtures of Factor Analysers

    Yichuan Tang, Ruslan Salakhutdinov, Geoffrey E. Hinton

    ICML (2012)

  •  

    Deep Neural Networks for Acoustic Modeling in Speech Recognition

    Geoffrey Hinton, Li Deng, Dong Yu, George Dahl, Abdel-rahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen, Tara Sainath, Brian Kingsbury

    Signal Processing Magazine (2012)

  •  

    Efficient Parametric Projection Pursuit Density Estimation

    Max Welling, Richard S. Zemel, Geoffrey E. Hinton

    CoRR, vol. abs/1212.2513 (2012)

  •  

    ImageNet Classification with Deep Convolutional Neural Networks

    Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton

    NIPS (2012), pp. 1106-1114

  •  

    Improving neural networks by preventing co-adaptation of feature detectors

    Geoffrey E. Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, Ruslan Salakhutdinov

    CoRR, vol. abs/1207.0580 (2012)

  •  

    Introduction to the Special Section on Deep Learning for Speech and Language Processing

    Dong Yu, Geoffrey E. Hinton, Nelson Morgan, Jen-Tzung Chien, Shigeki Sagayama

    IEEE Trans. Audio, Speech & Language Processing, vol. 20 (2012), pp. 4-6

  •  

    Learning to Label Aerial Images from Noisy Data

    Volodymyr Mnih, Geoffrey E. Hinton

    ICML (2012)

  •  

    Products of Hidden Markov Models: It Takes N>1 to Tango

    Graham W. Taylor, Geoffrey E. Hinton

    CoRR, vol. abs/1205.2614 (2012)

  •  

    Robust Boltzmann Machines for recognition and denoising

    Yichuan Tang, Ruslan Salakhutdinov, Geoffrey E. Hinton

    CVPR (2012), pp. 2264-2271

  •  

    Understanding how Deep Belief Networks perform acoustic modelling

    Abdel-rahman Mohamed, Geoffrey E. Hinton, Gerald Penn

    ICASSP (2012), pp. 4273-4276

  •  

    Visualizing non-metric similarities in multiple maps

    Laurens van der Maaten, Geoffrey E. Hinton

    Machine Learning, vol. 87 (2012), pp. 33-55

  •  

    A better way to learn features: technical perspective

    Geoffrey E. Hinton

    Commun. ACM, vol. 54 (2011), pp. 94

  •  

    Conditional Restricted Boltzmann Machines for Structured Output Prediction

    Volodymyr Mnih, Hugo Larochelle, Geoffrey E. Hinton

    UAI (2011), pp. 514-522

  •  

    Deep Belief Networks using discriminative features for phone recognition

    Abdel-rahman Mohamed, Tara N. Sainath, George E. Dahl, Bhuvana Ramabhadran, Geoffrey E. Hinton, Michael A. Picheny

    ICASSP (2011), pp. 5060-5063

  •  

    Deep belief nets for natural language call-routing

    Ruhi Sarikaya, Geoffrey E. Hinton, Bhuvana Ramabhadran

    ICASSP (2011), pp. 5680-5683

  •  

    Discovering Binary Codes for Documents by Learning Deep Generative Models

    Geoffrey E. Hinton, Ruslan Salakhutdinov

    topiCS, vol. 3 (2011), pp. 74-91

  •  

    Generating Text with Recurrent Neural Networks

    Ilya Sutskever, James Martens, Geoffrey E. Hinton

    ICML (2011), pp. 1017-1024

  •  

    Learning a better representation of speech soundwaves using restricted boltzmann machines

    Navdeep Jaitly, Geoffrey E. Hinton

    ICASSP (2011), pp. 5884-5887

  •  

    Modeling the joint density of two images under a variety of transformations

    Joshua M. Susskind, Geoffrey E. Hinton, Roland Memisevic, Marc Pollefeys

    CVPR (2011), pp. 2793-2800

  •  

    On deep generative models with applications to recognition

    Marc'Aurelio Ranzato, Joshua M. Susskind, Volodymyr Mnih, Geoffrey E. Hinton

    CVPR (2011), pp. 2857-2864

  •  

    Transforming Auto-Encoders

    Geoffrey E. Hinton, Alex Krizhevsky, Sida D. Wang

    ICANN (1) (2011), pp. 44-51

  •  

    Two Distributed-State Models For Generating High-Dimensional Time Series

    Graham W. Taylor, Geoffrey E. Hinton, Sam T. Roweis

    Journal of Machine Learning Research, vol. 12 (2011), pp. 1025-1068

  •  

    Using very deep autoencoders for content-based image retrieval

    Alex Krizhevsky, Geoffrey E. Hinton

    ESANN (2011)

  •  

    Binary coding of speech spectrograms using a deep auto-encoder

    Li Deng, Michael L. Seltzer, Dong Yu, Alex Acero, Abdel-rahman Mohamed, Geoffrey E. Hinton

    INTERSPEECH (2010), pp. 1692-1695

  •  

    Boltzmann Machines

    Geoffrey E. Hinton

    Encyclopedia of Machine Learning (2010), pp. 132-136

  •  

    Comparing Classification Methods for Longitudinal fMRI Studies

    Tanya Schmah, Grigori Yourganov, Richard S. Zemel, Geoffrey E. Hinton, Steven L. Small, Stephen C. Strother

    Neural Computation, vol. 22 (2010), pp. 2729-2762

  •  

    Deep Belief Nets

    Geoffrey E. Hinton

    Encyclopedia of Machine Learning (2010), pp. 267-269

  •  

    Dynamical binary latent variable models for 3D human pose tracking

    Graham W. Taylor, Leonid Sigal, David J. Fleet, Geoffrey E. Hinton

    CVPR (2010), pp. 631-638

  •  

    Factored 3-Way Restricted Boltzmann Machines For Modeling Natural Images

    Marc'Aurelio Ranzato, Alex Krizhevsky, Geoffrey E. Hinton

    AISTATS (2010), pp. 621-628

  •  

    Gated Softmax Classification

    Roland Memisevic, Christopher Zach, Geoffrey E. Hinton, Marc Pollefeys

    NIPS (2010), pp. 1603-1611

  •  

    Generating more realistic images using gated MRF's

    Marc'Aurelio Ranzato, Volodymyr Mnih, Geoffrey E. Hinton

    NIPS (2010), pp. 2002-2010

  •  

    Learning to Detect Roads in High-Resolution Aerial Images

    Volodymyr Mnih, Geoffrey E. Hinton

    ECCV (6) (2010), pp. 210-223

  •  

    Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines

    Roland Memisevic, Geoffrey E. Hinton

    Neural Computation, vol. 22 (2010), pp. 1473-1492

  •  

    Learning to combine foveal glimpses with a third-order Boltzmann machine

    Hugo Larochelle, Geoffrey E. Hinton

    NIPS (2010), pp. 1243-1251

  •  

    Modeling pixel means and covariances using factorized third-order boltzmann machines

    Marc'Aurelio Ranzato, Geoffrey E. Hinton

    CVPR (2010), pp. 2551-2558

  •  

    Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine

    George E. Dahl, Marc'Aurelio Ranzato, Abdel-rahman Mohamed, Geoffrey E. Hinton

    NIPS (2010), pp. 469-477

  •  

    Phone recognition using Restricted Boltzmann Machines

    Abdel-rahman Mohamed, Geoffrey E. Hinton

    ICASSP (2010), pp. 4354-4357

  •  

    Rectified Linear Units Improve Restricted Boltzmann Machines

    Vinod Nair, Geoffrey E. Hinton

    ICML (2010), pp. 807-814

  •  

    Temporal-Kernel Recurrent Neural Networks

    Ilya Sutskever, Geoffrey E. Hinton

    Neural Networks, vol. 23 (2010), pp. 239-243

  •  

    3D Object Recognition with Deep Belief Nets

    Vinod Nair, Geoffrey E. Hinton

    NIPS (2009), pp. 1339-1347

  •  

    Deep Boltzmann Machines

    Ruslan Salakhutdinov, Geoffrey E. Hinton

    AISTATS (2009), pp. 448-455

  •  

    Deep belief networks

    Geoffrey E. Hinton

    Scholarpedia, vol. 4 (2009), pp. 5947

  •  

    Factored conditional restricted Boltzmann Machines for modeling motion style

    Graham W. Taylor, Geoffrey E. Hinton

    ICML (2009), pp. 1025-1032

  •  

    Improving a statistical language model through non-linear prediction

    Andriy Mnih, Zhang Yuecheng, Geoffrey E. Hinton

    Neurocomputing, vol. 72 (2009), pp. 1414-1418

  •  

    Learning Generative Texture Models with extended Fields-of-Experts

    Nicolas Heess, Christopher K. I. Williams, Geoffrey E. Hinton

    BMVC (2009), pp. 1-11

  •  

    Modeling pigeon behavior using a Conditional Restricted Boltzmann Machine

    Matthew D. Zeiler, Graham W. Taylor, Nikolaus F. Troje, Geoffrey E. Hinton

    ESANN (2009)

  •  

    Products of Hidden Markov Models: It Takes N>1 to Tango

    Graham W. Taylor, Geoffrey E. Hinton

    UAI (2009), pp. 522-529

  •  

    Replicated Softmax: an Undirected Topic Model

    Ruslan Salakhutdinov, Geoffrey E. Hinton

    NIPS (2009), pp. 1607-1614

  •  

    Semantic hashing

    Ruslan Salakhutdinov, Geoffrey E. Hinton

    Int. J. Approx. Reasoning, vol. 50 (2009), pp. 969-978

  •  

    Using fast weights to improve persistent contrastive divergence

    Tijmen Tieleman, Geoffrey E. Hinton

    ICML (2009), pp. 1033-1040

  •  

    Workshop summary: Workshop on learning feature hierarchies

    Kai Yu, Ruslan Salakhutdinov, Yann LeCun, Geoffrey E. Hinton, Yoshua Bengio

    ICML (2009), pp. 5

  •  

    Zero-shot Learning with Semantic Output Codes

    Mark Palatucci, Dean Pomerleau, Geoffrey E. Hinton, Tom M. Mitchell

    NIPS (2009), pp. 1410-1418

  •  

    A Scalable Hierarchical Distributed Language Model

    Andriy Mnih, Geoffrey E. Hinton

    NIPS (2008), pp. 1081-1088

  •  

    Analysis-by-Synthesis by Learning to Invert Generative Black Boxes

    Vinod Nair, Joshua M. Susskind, Geoffrey E. Hinton

    ICANN (1) (2008), pp. 971-981

  •  

    Deep, Narrow Sigmoid Belief Networks Are Universal Approximators

    Ilya Sutskever, Geoffrey E. Hinton

    Neural Computation, vol. 20 (2008), pp. 2629-2636

  •  

    Generative versus discriminative training of RBMs for classification of fMRI images

    Tanya Schmah, Geoffrey E. Hinton, Richard S. Zemel, Steven L. Small, Stephen C. Strother

    NIPS (2008), pp. 1409-1416

  •  

    Implicit Mixtures of Restricted Boltzmann Machines

    Vinod Nair, Geoffrey E. Hinton

    NIPS (2008), pp. 1145-1152

  •  

    Improving a statistical language model by modulating the effects of context words

    Zhang Yuecheng, Andriy Mnih, Geoffrey E. Hinton

    ESANN (2008), pp. 493-498

  •  

    The Recurrent Temporal Restricted Boltzmann Machine

    Ilya Sutskever, Geoffrey E. Hinton, Graham W. Taylor

    NIPS (2008), pp. 1601-1608

  •  

    Using matrices to model symbolic relationship

    Ilya Sutskever, Geoffrey E. Hinton

    NIPS (2008), pp. 1593-1600

  •  

    Boltzmann machine

    Geoffrey E. Hinton

    Scholarpedia, vol. 2 (2007), pp. 1668

  •  

    Learning Multilevel Distributed Representations for High-Dimensional Sequences

    Ilya Sutskever, Geoffrey E. Hinton

    AISTATS (2007), pp. 548-555

  •  

    Learning a Nonlinear Embedding by Preserving Class Neighbourhood Structure

    Ruslan Salakhutdinov, Geoffrey E. Hinton

    AISTATS (2007), pp. 412-419

  •  

    Modeling image patches with a directed hierarchy of Markov random fields

    Simon Osindero, Geoffrey E. Hinton

    NIPS (2007), pp. 1121-1128

  •  

    Restricted Boltzmann machines for collaborative filtering

    Ruslan Salakhutdinov, Andriy Mnih, Geoffrey E. Hinton

    ICML (2007), pp. 791-798

  •  

    Three new graphical models for statistical language modelling

    Andriy Mnih, Geoffrey E. Hinton

    ICML (2007), pp. 641-648

  •  

    Unsupervised Learning of Image Transformations

    Roland Memisevic, Geoffrey E. Hinton

    CVPR (2007)

  •  

    Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes

    Ruslan Salakhutdinov, Geoffrey E. Hinton

    NIPS (2007), pp. 1249-1256

  •  

    Visualizing Similarity Data with a Mixture of Maps

    James Cook, Ilya Sutskever, Andriy Mnih, Geoffrey E. Hinton

    AISTATS (2007), pp. 67-74

  •  

    A Fast Learning Algorithm for Deep Belief Nets

    Geoffrey E. Hinton, Simon Osindero, Yee Whye Teh

    Neural Computation, vol. 18 (2006), pp. 1527-1554

  •  

    Modeling Human Motion Using Binary Latent Variables

    Graham W. Taylor, Geoffrey E. Hinton, Sam T. Roweis

    NIPS (2006), pp. 1345-1352

  •  

    Topographic Product Models Applied to Natural Scene Statistics

    Simon Osindero, Max Welling, Geoffrey E. Hinton

    Neural Computation, vol. 18 (2006), pp. 381-414

  •  

    Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation

    Geoffrey E. Hinton, Simon Osindero, Max Welling, Yee Whye Teh

    Cognitive Science, vol. 30 (2006), pp. 725-731

  •  

    Improving dimensionality reduction with spectral gradient descent

    Roland Memisevic, Geoffrey E. Hinton

    Neural Networks, vol. 18 (2005), pp. 702-710

  •  

    Inferring Motor Programs from Images of Handwritten Digits

    Geoffrey E. Hinton, Vinod Nair

    NIPS (2005), pp. 515-522

  •  

    Learning Causally Linked Markov Random Fields

    Geoffrey E. Hinton, Simon Osindero, Kejie Bao

    AISTATS (2005)

  •  

    On Contrastive Divergence Learning

    Miguel Á. Carreira-Perpiñán, Geoffrey Hinton

    AISTATS (2005)

  •  

    What kind of graphical model is the brain?

    Geoffrey E. Hinton

    IJCAI (2005), pp. 1765-

  •  

    Exponential Family Harmoniums with an Application to Information Retrieval

    Max Welling, Michal Rosen-Zvi, Geoffrey E. Hinton

    NIPS (2004), pp. 1481-1488

  •  

    Multiple Relational Embedding

    Roland Memisevic, Geoffrey E. Hinton

    NIPS (2004), pp. 913-920

  •  

    Neighbourhood Components Analysis

    Jacob Goldberger, Sam T. Roweis, Geoffrey E. Hinton, Ruslan Salakhutdinov

    NIPS (2004), pp. 513-520

  •  

    Probabilistic sequential independent components analysis

    Max Welling, Richard S. Zemel, Geoffrey E. Hinton

    IEEE Trans. Neural Networks, vol. 15 (2004), pp. 838-849

  •  

    Reinforcement Learning with Factored States and Actions

    Brian Sallans, Geoffrey E. Hinton

    Journal of Machine Learning Research, vol. 5 (2004), pp. 1063-1088

  •  

    Efficient Parametric Projection Pursuit Density Estimation

    Max Welling, Richard S. Zemel, Geoffrey E. Hinton

    UAI (2003), pp. 575-582

  •  

    Energy-Based Models for Sparse Overcomplete Representations

    Yee Whye Teh, Max Welling, Simon Osindero, Geoffrey E. Hinton

    Journal of Machine Learning Research, vol. 4 (2003), pp. 1235-1260

  •  

    Wormholes Improve Contrastive Divergence

    Geoffrey E. Hinton, Max Welling, Andriy Mnih

    NIPS (2003), pp. 417-424

  •  

    A Desktop Input Device and Interface for Interactive 3D Character Animation

    Sageev Oore, Demetri Terzopoulos, Geoffrey E. Hinton

    Graphics Interface (2002), pp. 133-140

  •  

    A New Learning Algorithm for Mean Field Boltzmann Machines

    Max Welling, Geoffrey E. Hinton

    ICANN (2002), pp. 351-357

  •  

    In Memory of Ray Reiter (1939-2002)

    Fiora Pirri, Geoffrey E. Hinton, Hector J. Levesque

    AI Magazine, vol. 23 (2002), pp. 93

  •  

    Learning Sparse Topographic Representations with Products of Student-t Distributions

    Max Welling, Geoffrey E. Hinton, Simon Osindero

    NIPS (2002), pp. 1359-1366

  •  

    Local Physical Models for Interactive Character Animation

    Sageev Oore, Demetri Terzopoulos, Geoffrey E. Hinton

    Comput. Graph. Forum, vol. 21 (2002), pp. 337-346

  •  

    Recognizing Handwritten Digits Using Hierarchical Products of Experts

    Guy Mayraz, Geoffrey E. Hinton

    IEEE Trans. Pattern Anal. Mach. Intell., vol. 24 (2002), pp. 189-197

  •  

    Self Supervised Boosting

    Max Welling, Richard S. Zemel, Geoffrey E. Hinton

    NIPS (2002), pp. 665-672

  •  

    Stochastic Neighbor Embedding

    Geoffrey E. Hinton, Sam T. Roweis

    NIPS (2002), pp. 833-840

  •  

    Training Products of Experts by Minimizing Contrastive Divergence

    Geoffrey E. Hinton

    Neural Computation, vol. 14 (2002), pp. 1771-1800

  •  

    Discovering Multiple Constraints that are Frequently Approximately Satisfied

    Geoffrey E. Hinton, Yee Whye Teh

    UAI (2001), pp. 227-234

  •  

    Global Coordination of Local Linear Models

    Sam T. Roweis, Lawrence K. Saul, Geoffrey E. Hinton

    NIPS (2001), pp. 889-896

  •  

    Learning Distributed Representations of Concepts Using Linear Relational Embedding

    Alberto Paccanaro, Geoffrey E. Hinton

    IEEE Trans. Knowl. Data Eng., vol. 13 (2001), pp. 232-244

  •  

    Learning Hierarchical Structures with Linear Relational Embedding

    Alberto Paccanaro, Geoffrey E. Hinton

    NIPS (2001), pp. 857-864

  •  

    Products of Hidden Markov Models

    Andrew D. Brown, Geoffrey E. Hinton

    AISTATS (2001)

  •  

    Relative Density Nets: A New Way to Combine Backpropagation with HMM's

    Andrew D. Brown, Geoffrey E. Hinton

    NIPS (2001), pp. 1149-1156

  •  

    Extracting Distributed Representations of Concepts and Relations from Positive and Negative Propositions

    Alberto Paccanaro, Geoffrey E. Hinton

    IJCNN (2) (2000), pp. 259-264

  •  

    Learning Distributed Representations by Mapping Concepts and Relations into a Linear Space

    Alberto Paccanaro, Geoffrey E. Hinton

    ICML (2000), pp. 711-718

  •  

    Modeling High-Dimensional Data by Combining Simple Experts

    Geoffrey E. Hinton

    AAAI/IAAI (2000), pp. 1159-1164

  •  

    Rate-coded Restricted Boltzmann Machines for Face Recognition

    Yee Whye Teh, Geoffrey E. Hinton

    NIPS (2000), pp. 908-914

  •  

    Recognizing Hand-written Digits Using Hierarchical Products of Experts

    Guy Mayraz, Geoffrey E. Hinton

    NIPS (2000), pp. 953-959

  •  

    SMEM Algorithm for Mixture Models

    Naonori Ueda, Ryohei Nakano, Zoubin Ghahramani, Geoffrey E. Hinton

    Neural Computation, vol. 12 (2000), pp. 2109-2128

  •  

    Split and Merge EM Algorithm for Improving Gaussian Mixture Density Estimates

    Naonori Ueda, Ryohei Nakano, Zoubin Ghahramani, Geoffrey E. Hinton

    VLSI Signal Processing, vol. 26 (2000), pp. 133-140

  •  

    Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task

    Brian Sallans, Geoffrey E. Hinton

    NIPS (2000), pp. 1075-1081

  •  

    Variational Learning for Switching State-Space Models

    Zoubin Ghahramani, Geoffrey E. Hinton

    Neural Computation, vol. 12 (2000), pp. 831-864

  •  

    Learning to Parse Images

    Geoffrey E. Hinton, Zoubin Ghahramani, Yee Whye Teh

    NIPS (1999), pp. 463-469

  •  

    Spiking Boltzmann Machines

    Geoffrey E. Hinton, Andrew D. Brown

    NIPS (1999), pp. 122-128

  •  

    Variational Learning in Nonlinear Gaussian Belief Networks

    Brendan J. Frey, Geoffrey E. Hinton

    Neural Computation, vol. 11 (1999), pp. 193-213

  •  

    Coaching variables for regression and classification

    Robert Tibshirani, Geoffrey Hinton

    Statistics and Computing, vol. 8 (1998), pp. 25-33

  •  

    Fast Neural Network Emulation of Dynamical Systems for Computer Animation

    Radek Grzeszczuk, Demetri Terzopoulos, Geoffrey E. Hinton

    NIPS (1998), pp. 882-888

  •  

    Glove-TalkII-a neural-network interface which maps gestures to parallel formant speech synthesizer controls

    S. Sidney Fels, Geoffrey E. Hinton

    IEEE Trans. Neural Networks, vol. 9 (1998), pp. 205-212

  •  

    NeuroAnimator: Fast Neural Network Emulation and Control of Physics-based Models

    Radek Grzeszczuk, Demetri Terzopoulos, Geoffrey E. Hinton

    SIGGRAPH (1998), pp. 9-20

  •  

    SMEM Algorithm for Mixture Models

    Naonori Ueda, Ryohei Nakano, Zoubin Ghahramani, Geoffrey E. Hinton

    NIPS (1998), pp. 599-605

  •  

    A Mobile Robot that Learns its Place

    Sageev Oore, Geoffrey E. Hinton, Gregory Dudek

    Neural Computation, vol. 9 (1997), pp. 683-699

  •  

    Efficient Stochastic Source Coding and an Application to a Bayesian Network Source Model

    Brendan J. Frey, Geoffrey E. Hinton

    Comput. J., vol. 40 (1997), pp. 157-165

  •  

    Glove-talk II - a neural-network interface which maps gestures to parallel formant speech synthesizer controls

    S. Sidney Fels, Geoffrey E. Hinton

    IEEE Trans. Neural Networks, vol. 8 (1997), pp. 977-984

  •  

    Hierarchical Non-linear Factor Analysis and Topographic Maps

    Zoubin Ghahramani, Geoffrey E. Hinton

    NIPS (1997), pp. 486-492

  •  

    Instantiating Deformable Models with a Neural Net

    Christopher K. I. Williams, Michael Revow, Geoffrey E. Hinton

    Computer Vision and Image Understanding, vol. 68 (1997), pp. 120-126

  •  

    Modeling the manifolds of images of handwritten digits

    Geoffrey E. Hinton, Peter Dayan, Michael Revow

    IEEE Trans. Neural Networks, vol. 8 (1997), pp. 65-74

  •  

    Using Expectation-Maximization for Reinforcement Learning

    Peter Dayan, Geoffrey E. Hinton

    Neural Computation, vol. 9 (1997), pp. 271-278

  •  

    Free Energy Coding

    Brendan J. Frey, Geoffrey E. Hinton

    Data Compression Conference (1996), pp. 73-81

  •  

    Varieties of Helmholtz Machine

    Peter Dayan, Geoffrey E. Hinton

    Neural Networks, vol. 9 (1996), pp. 1385-1403

  •  

    Does the Wake-sleep Algorithm Produce Good Density Estimators?

    Brendan J. Frey, Geoffrey E. Hinton, Peter Dayan

    NIPS (1995), pp. 661-667

  •  

    GloveTalkII: An Adaptive Gesture-to-Formant Interface

    Sidney Fels, Geoffrey E. Hinton

    CHI (1995), pp. 456-463

  •  

    The Helmholtz machine

    Peter Dayan, Geoffrey E. Hinton, Radford M. Neal, Richard S. Zemel

    Neural Computation, vol. 7 (1995), pp. 889-904

  •  

    Using Pairs of Data-Points to Define Splits for Decision Trees

    Geoffrey E. Hinton, Michael Revow

    NIPS (1995), pp. 507-513

  •  

    An Alternative Model for Mixtures of Experts

    Lei Xu 0001, Michael I. Jordan, Geoffrey E. Hinton

    NIPS (1994), pp. 633-640

  •  

    Glove-TalkII: Mapping Hand Gestures to Speech Using Neural Networks

    Sidney Fels, Geoffrey E. Hinton

    NIPS (1994), pp. 843-850

  •  

    Recognizing Handwritten Digits Using Mixtures of Linear Models

    Geoffrey E. Hinton, Michael Revow, Peter Dayan

    NIPS (1994), pp. 1015-1022

  •  

    A soft decision-directed LMS algorithm for blind equalization

    Steven J. Nowlan, Geoffrey E. Hinton

    IEEE Trans. Communications, vol. 41 (1993), pp. 275-279

  •  

    Autoencoders, Minimum Description Length and Helmholtz Free Energy

    Geoffrey E. Hinton, Richard S. Zemel

    NIPS (1993), pp. 3-10

  •  

    Developing Population Codes by Minimizing Description Length

    Richard S. Zemel, Geoffrey E. Hinton

    NIPS (1993), pp. 11-18

  •  

    Glove-Talk: a neural network interface between a data-glove and a speech synthesizer

    S. Sidney Fels, Geoffrey E. Hinton

    IEEE Trans. Neural Networks, vol. 4 (1993), pp. 2-8

  •  

    Keeping the Neural Networks Simple by Minimizing the Description Length of the Weights

    Geoffrey E. Hinton, Drew van Camp

    COLT (1993), pp. 5-13

  •  

    Learning Mixture Models of Spatial Coherence

    Suzanna Becker, Geoffrey E. Hinton

    Neural Computation, vol. 5 (1993), pp. 267-277

  •  

    Feudal Reinforcement Learning

    Peter Dayan, Geoffrey E. Hinton

    NIPS (1992), pp. 271-278

  •  

    Simplifying Neural Networks by Soft Weight-Sharing

    Steven J. Nowlan, Geoffrey E. Hinton

    Neural Computation, vol. 4 (1992), pp. 473-493

  •  

    Adaptive Mixtures of Local Experts

    Robert A. Jacobs, Michael I. Jordan, Steven J. Nowlan, Geoffrey E. Hinton

    Neural Computation, vol. 3 (1991), pp. 79-87

  •  

    Adaptive Soft Weight Tying using Gaussian Mixtures

    Steven J. Nowlan, Geoffrey E. Hinton

    NIPS (1991), pp. 993-1000

  •  

    Learning to Make Coherent Predictions in Domains with Discontinuities

    Suzanna Becker, Geoffrey E. Hinton

    NIPS (1991), pp. 372-379

  •  

    A time-delay neural network architecture for isolated word recognition

    Kevin J. Lang, Alex Waibel, Geoffrey E. Hinton

    Neural Networks, vol. 3 (1990), pp. 23-43

  •  

    Building adaptive interfaces with neural networks: The glove-talk pilot study

    Sidney Fels, Geoffrey E. Hinton

    INTERACT (1990), pp. 683-688

  •  

    Connectionist Symbol Processing - Preface

    Geoffrey E. Hinton

    Artif. Intell., vol. 46 (1990), pp. 1-4

  •  

    Discovering Viewpoint-Invariant Relationships That Characterize Objects

    Richard S. Zemel, Geoffrey E. Hinton

    NIPS (1990), pp. 299-305

  •  

    Evaluation of Adaptive Mixtures of Competing Experts

    Steven J. Nowlan, Geoffrey E. Hinton

    NIPS (1990), pp. 774-780

  •  

    Mapping Part-Whole Hierarchies into Connectionist Networks

    Geoffrey E. Hinton

    Artif. Intell., vol. 46 (1990), pp. 47-75

  •  

    The Bootstrap Widrow-Hoff Rule as a Cluster-Formation Algorithm

    Geoffrey E. Hinton, Steven J. Nowlan

    Neural Computation, vol. 2 (1990), pp. 355-362

  •  

    Connectionist Learning Procedures

    Geoffrey E. Hinton

    Artif. Intell., vol. 40 (1989), pp. 185-234

  •  

    Deterministic Boltzmann Learning Performs Steepest Descent in Weight-Space

    Geoffrey E. Hinton

    Neural Computation, vol. 1 (1989), pp. 143-150

  •  

    Dimensionality Reduction and Prior Knowledge in E-Set Recognition

    Kevin J. Lang, Geoffrey E. Hinton

    NIPS (1989), pp. 178-185

  •  

    Discovering High Order Features with Mean Field Modules

    Conrad C. Galland, Geoffrey E. Hinton

    NIPS (1989), pp. 509-515

  •  

    Phoneme recognition using time-delay neural networks

    Alexander H. Waibel, Toshiyuki Hanazawa, Geoffrey E. Hinton, Kiyohiro Shikano, Kevin J. Lang

    IEEE Trans. Acoustics, Speech, and Signal Processing, vol. 37 (1989), pp. 328-339

  •  

    TRAFFIC: Recognizing Objects Using Hierarchical Reference Frame Transformations

    Richard S. Zemel, Michael Mozer, Geoffrey E. Hinton

    NIPS (1989), pp. 266-273

  •  

    A Distributed Connectionist Production System

    David S. Touretzky, Geoffrey E. Hinton

    Cognitive Science, vol. 12 (1988), pp. 423-466

  •  

    GEMINI: Gradient Estimation Through Matrix Inversion After Noise Injection

    Yann LeCun, Conrad C. Galland, Geoffrey E. Hinton

    NIPS (1988), pp. 141-148

  •  

    Connectionist Architectures for Artificial Intelligence

    Scott E. Fahlman, Geoffrey E. Hinton

    IEEE Computer, vol. 20 (1987), pp. 100-109

  •  

    Learning Representations by Recirculation

    Geoffrey E. Hinton, James L. McClelland

    NIPS (1987), pp. 358-366

  •  

    Learning Translation Invariant Recognition in Massively Parallel Networks

    Geoffrey E. Hinton

    PARLE (1) (1987), pp. 1-13

  •  

    Learning in Massively Parallel Nets (Panel)

    Drew V. McDermott, Geoffrey E. Hinton

    AAAI (1986), pp. 1149

  •  

    A Learning Algorithm for Boltzmann Machines

    David H. Ackley, Geoffrey E. Hinton, Terrence J. Sejnowski

    Cognitive Science, vol. 9 (1985), pp. 147-169

  •  

    Shape Recognition and Illusory Conjunctions

    Geoffrey E. Hinton, Kevin J. Lang

    IJCAI (1985), pp. 252-259

  •  

    Symbols Among the Neurons: Details of a Connectionist Inference Architecture

    David S. Touretzky, Geoffrey E. Hinton

    IJCAI (1985), pp. 238-243

  •  

    Massively Parallel Architectures for AI: NETL, Thistle, and Boltzmann Machines

    Scott E. Fahlman, Geoffrey E. Hinton, Terrence J. Sejnowski

    AAAI (1983), pp. 109-113

  •  

    A Parallel Computation that Assigns Canonical Object-Based Frames of Reference

    Geoffrey E. Hinton

    IJCAI (1981), pp. 683-685

  •  

    Shape Representation in Parallel Systems

    Geoffrey E. Hinton

    IJCAI (1981), pp. 1088-1096

  •  

    Some Demonstrations of the Effects of Structural Descriptions in Mental Imagery

    Geoffrey E. Hinton

    Cognitive Science, vol. 3 (1979), pp. 231-250

  •  

    Representation and Control in Vision

    Aaron Sloman, David Owen, Geoffrey E. Hinton, Frank Birch, Frank O'Gorman

    AISB/GI (ECAI) (1978), pp. 309-314

  •  

    Using Relaxation to find a Puppet

    Geoffrey E. Hinton

    AISB (ECAI) (1976), pp. 148-157