Hinton, Geoffrey E. - Department of Computer Science, University of Toronto

• Introduction variational
• The Helmholtz Machine Peter Dayan 1 Geoffrey E Hinton 1 Radford M Neal 1 Richard S Zemel 2
• CSC2535: 2011 Learning Deep BoltzmanMachines
• Department of Computer Science 6 King's College Rd, Toronto University of Toronto M5S 3G4, Canada
• CSC2535: Computation in Neural Networks Variational Bayesian Learning & Model Selection
• A simple algorithm that discovers e cient perceptual codes
• Berkes, P. and Wiskott, L. (2003). Slow feature analysis yields a rich repertoire of complex cell properties. Cognitive Sciences EPrint Archive (CogPrints) 2804,
• Copyright Cambridge University Press 2003. On-screen viewing permitted. Printing not permitted. http://www.cambridge.org/0521642981 You can buy this book for 30 pounds or $50. See http://www.inference.phy.cam.ac.uk/mackay/itila/ for links.
• CSC321: Introduction to Neural Networks and Machine Learning
• CSC321: Tutorial with extra material on: Semantic Hashing
• CSC2515: Lecture Independent
• Recognizing Handwritten Digits Using Hierarchical Products of Experts
• Learning Causally Linked Markov Random Fields G. E. Hinton, S. Osindero and K. Bao
• Products of Hidden Markov Models Andrew D. Brown
• To appear in Jordan, MI, Kearns MJ, and Solla, SA Advances in Neural Information Processing Systems 10. MIT Press: Cambridge, MA, 1998.
• Modeling the joint density of two images under a variety of transformations Joshua Susskind
• CSC321: 2011 Introduction to Neural Networks
• CSC2515 Assignment 2 Due Nov 5 2008, 1.00pm at START of class
• CSC2515 Fall 2008 Introduction to Machine Learning
• Introduction www.cs.toronto.edu/~hinton
• CSC2515 Assignment 3 Due: Nov 20 2007, 11am at START of class
• Copyright Cambridge University Press 2003. On-screen viewing permitted. Printing not permitted. http://www.cambridge.org/0521642981 You can buy this book for 30 pounds or $50. See http://www.inference.phy.cam.ac.uk/mackay/itila/ for links.
• 1 An Introduction to Conditional Random Fields for Relational Learning
• CSC2515 Assignment 2 Due Oct 30 2007, 11am at START of class
• Appendix to Lecture 4: Introduction to
• CSC2535: Computation in Neural Networks Variational Bayesian Learning & Model Selection
• Copyright Cambridge University Press 2003. Onscreen viewing permitted. Printing not permitted. http://www.cambridge.org/0521642981 You can buy this book for 30 pounds or $50. See http://www.inference.phy.cam.ac.uk/mackay/itila/ for links.
• csc2535 2011 Recognizing speech.
• CSC321: Neural Networks Lecture 13: Learning without a teacher
• CSC321: 2011 Introduction to Neural Networks
• CSC2535: 2011 Advanced Machine Learning
• Introduction to Neural Networks and Machine Learning
• Generative Models for Discovering Sparse Distributed Representations
• COMPUTER VISION IMAGE UNDERSTANDING October, 120--126,
• Stochastic Neighbor Embedding Geoffrey Hinton and Sam Roweis
• Learning multiple layers of representation
• Inferring Motor Programs from Images of Handwritten Digits
• Unsupervised Discovery of NonLinear Structure using Contrastive Backpropagation
• A Tutorial on BoostingA Tutorial on BoostingA Tutorial on BoostingA Tutorial on BoostingA Tutorial on Boosting Yoav Freund
• What kind of a graphical model is the brain? Geoffrey E. Hinton
• 6: Hopfield nets (contd.) Kevin Gurney
• 5: Associative memories the Hopfield net Kevin Gurney
• Extracting Distributed Representations of Concepts and Relations from Positive and Negative Propositions
• Global Coordination of Local Linear Models Sam Roweis y , Lawrence K. Saul yy , and Geoffrey E. Hinton y
• A fast learning algorithm for deep belief nets # Geoffrey E. Hinton and Simon Osindero
• LETTER Communicated by Yann Le Cun A Fast Learning Algorithm for Deep Belief Nets
• In Neural Computation, 3, pages 79-87. Adaptive Mixtures of Local Experts
• COGNITIVE SCIENCE 9, 147-169 (1985) A LearningAlgorithm for
• CSC2515 FALL 2008 INTRODUCTION TO MACHINE LEARNING
• Training Restricted Boltzmann Machines using Approximations to the Likelihood Gradient
• CSC321: 2011 Introduction to Neural Networks
• Introduction to Neural Networks and Machine Lecture 15: Mixtures of Experts
• Computer Speech and Language (1987) 2, 35-61 Learning sets of filters using
• Gated Softmax Classification Roland Memisevic
• MATLAB for complete novices Roland Memisevic
• NeuroAnimator: Fast Neural Network Emulation and Control of Physics-Based Models
• TRAINING MANY SMALL HIDDEN MARKOV MODELS G. E. Hinton Gatsby Computational Neuroscience Unit, University College London,
• In Advances in Neural Information Processing Systems 12 S.A. Solla, T.K. Leen and K.-R. Muller (eds.), 463{469,
• multilayer discriminative
• CSC321: 2011 Introduction to Neural Networks
• COGNITIVE SCIENCE 3, 231-250 (1979) Some Demonstrations of the Effects
• USER'S GUIDE FOR T-SNE SOFTWARE User's Guide for t-SNE Software
• Keeping Neural Networks Simple by Minimizing the Description Length of the Weights
• Introduction Classification
• Introduction to Neural Networks and Machine Learning
• Introduction to Neural Networks and Machine Learning
• CSC2535 Assignment 1 February 2, 2011
• CSC2535 Two Suggestions for Projects Geoffrey Hinton
• CSC2535 Spring 2011 Lecture 1: Introduction to Machine
• CSC2535: 2011 Object Recognition and Information
• CSC 2535: 2011 Approximate inference in
• CSC2535 Spring 2010 Advanced Machine Learning
• Small codes and large image databases for recognition Antonio Torralba
• In Network: Computation in Neural Systems 9(1) 1998. Cascaded Redundancy Reduction
• Neighbourhood Components Analysis Jacob Goldberger, Sam Roweis, Geoff Hinton, Ruslan Salakhutdinov
• ARTIFICIAL INTELLIGENCE 47 Mapping Part-Whole Hierarchies into
• Wormholes Improve Contrastive Divergence Geoffrey Hinton, Max Welling
• Introduction www.cs.toronto.edu/~hinton
• Spiking Boltzmann Machines Geoffrey E. Hinton
• The setup for measuring the SHG is described in the supporting online material (22). We expect
• STATISTICS IN MEDICINE Statist. Med. 17, 2501--2508 (1998)
• Factored 3-Way Restricted Boltzmann Machines For Modeling Natural Images
• Journal of Machine Learning Research 5 (2004) 10631088 Submitted 3/02; Revised 1/04; Published 8/04 Reinforcement Learning with Factored States and Actions
• CognitioPl,30 (198$) l-35 viewer-centered (i.e., heod-
• CSC321: 2011 Introduction to Neural Networks
• The Recurrent Temporal Restricted Boltzmann Ilya Sutskever, Geoffrey Hinton, and Graham Taylor
• A VIEW OF THE EM ALGORITHM THAT JUSTIFIES INCREMENTAL, SPARSE, AND OTHER VARIANTS
• Modeling Human Motion Using Binary Latent Variables
• Visualizing Similarity Data with a Mixture of Maps James Cook, Ilya Sutskever, Andriy Mnih and Geoffrey Hinton
• Self Supervised Boosting Max Welling, Richard S. Zemel, and Geoffrey E. Hinton
• Machine Learning in MATLAB Roland Memisevic
• ``Coaching'' variables for regression and classification
• Collaborative Filtering and the Missing at Random Assumption Benjamin M. Marlin
• www.sciencemag.org/cgi/content/full/313/5786/504/DC1 Supporting Online Material for
• Learning Nonlinear Constraints with Contrastive Backpropagation
• In Neural Computation, 3, pages 7987. Adaptive Mixtures of Local Experts
• Inferring Motor Programs from Images of Handwritten Digits
• Using Free Energies to Represent Qvalues in a Multiagent Reinforcement Learning Task
• CSC321: 2011 Introduction to Neural Networks and
• Deep Boltzmann Machines Ruslan Salakhutdinov
• Scaling in a Hierarchical Unsupervised Network1 Zoubin Ghahramani,2
• Advanced Machine Learning Lecture 11b
• Using Mixtures of Factor Analyzers for Segmentation and Pose Estimation
• Autoencoders, Minimum Description Length and Helmholtz Free Energy
• To appear in: Neural Computation, 7:3, 1995. Learning Population Codes by
• CSC321: Introduction to Neural Networks and Machine Learning
• A Scalable Hierarchical Distributed Language Model Andriy Mnih
• Global Coordination of Local Linear Models , Lawrence K. Saul
• Minimizing Description Length in an Unsupervised Neural Network
• G-Maximization: an Unsupervised Learning Procedure for Discovering Regularities
• CSC321: Introduction to Neural Networks and machine Learning
• To appear in: Neural Computation, 7:3, 1995. Learning Population Codes by
• Training recurrent neural networks to generate text
• Keeping Neural Networks Simple by Minimizing the Description Length of the Weights
• Unsupervised Discovery of NonLinear Structure using Contrastive Backpropagation
• Variational Learning in NonLinear Gaussian Belief Networks
• 3D Object Recognition with Deep Belief Nets Vinod Nair and Geoffrey E. Hinton
• In: Procccdings of the AAAI-83confcrence Washington D.C.August 1983.
• Boltzmann Machines Geoffrey E. Hinton
• Introduction to Neural Networks and Machine Learning
• Introduction www.cs.toronto.edu/~hinton
• generalization complicated
• CSC2535 2011 Learning Multiplicative
• Replicated Softmax: an Undirected Topic Model Ruslan Salakhutdinov
• Topographic Product Models Applied To Natural Scene Statistics
• Proceedings of t h e IEEE Conference on Computer Vision and P a t t e r n Recognition Washington, D. C., June, 1983
• ARTIFICIAL INTELLIGENCE 1 Preface to the Special Issue on
• Developing Population Codes By Minimizing Description Length
• Learning hierarchical structures with Linear Relational Embedding
• Monte Carlo Methods for Inference and Learning
• Introduction to Neural Networks and Machine Learning
• Learning Nonlinear Constraints with Contrastive Backpropagation
• Discovering Multiple Constraints that are Frequently Approximately Satis ed
• Introduction Backpropagation
• Probability Probability
• Using EM for Reinforcement Learning Peter Dayan Geoffrey E Hinton
• Developing Population Codes By Minimizing Description Length
• A HIERARCHICAL COMMUNITY OF EXPERTS GEOFFREY E. HINTON
• Dimensionality reduction: Some Assumptions
• Learning Distributed Representations by Mapping Concepts and Relations into a Linear Space
• Ratecoded Restricted Boltzmann Machines for Face Recognition
• Products of Experts Geo rey E. Hinton
• Scaling in a Hierarchical Unsupervised Network 1 Zoubin Ghahramani, 2 Alexander T. Korenberg and Geoffrey E. Hinton
• Department of Computer Science 6 King's College Rd, Toronto University of Toronto M5S 3G4, Canada
• In Network: Computation in Neural Systems 9(1) 1998. Cascaded Redundancy Reduction
• Coaching" variables for regression and classi cation
• Using Pairs of Data-Points to De ne Splits for Decision Trees
• Exponential Family Harmoniums with an Application to Information Retrieval
• Ecient Parametric Projection Pursuit Density Estimation Max Welling
• Learning hierarchical structures with Linear Relational Embedding
• Learning Stochastic Feedforward Networks Radford M. Neal
• A NEW VIEW OF ICA G.E. Hinton, M. Welling, Y.W. Teh
• UCL Tutorial on: Deep Belief Nets
• 2007 NIPS Tutorial on: Deep Belief Nets
• Department of Computer Science 6 King's College Rd, Toronto University of Toronto M5S 3G4, Canada
• Transforming Auto-encoders G. E. Hinton, A. Krizhevsky & S. D. Wang
• LEARNING A BETTER REPRESENTATION OF SPEECH SOUND WAVES USING RESTRICTED BOLTZMANN MACHINES
• Learning to combine foveal glimpses with a third-order Boltzmann machine
• Rectified Linear Units Improve Restricted Boltzmann Machines Vinod Nair vnair@cs.toronto.edu
• doi: 10.1098/rstb.2009.0200 , 177-1843652010Phil. Trans. R. Soc. B
• Learning to Detect Roads in High-Resolution Aerial Volodymyr Mnih and Geoffrey E. Hinton
• Modeling Pixel Means and Covariances Using Factorized Third-Order Boltzmann Machines
• PHONE RECOGNITION USING RESTRICTED BOLTZMANN MACHINES Abdel-rahman Mohamed and Geoffrey Hinton
• Zero-Shot Learning with Semantic Output Codes Mark Palatucci
• Products of Hidden Markov Models: It Takes N>1 to Tango
• Factored Conditional Restricted Boltzmann Machines for Modeling Motion Style
• Using Fast Weights to Improve Persistent Contrastive Divergence Tijmen Tieleman tijmen@cs.toronto.edu
• Using matrices to model symbolic relationships Ilya Sutskever and Geoffrey Hinton
• Generative versus discriminative training of RBMs for classification of fMRI images
• Generating Facial Expressions with Deep Belief Nets
• Improving a statistical language model by modulating the effects of context words
• NOTE Communicated by Yoshua Bengio Deep, Narrow Sigmoid Belief Networks Are Universal
• Modeling image patches with a directed hierarchy of Markov random fields
• DRAFT. A revised version will appear in NIPS 2007. Using Deep Belief Nets to Learn Covariance Kernels
• Restricted Boltzmann Machines for Collaborative Filtering
• Three New Graphical Models for Statistical Language Modelling Andriy Mnih amnih@cs.toronto.edu
• Semantic Hashing Ruslan Salakhutdinov
• Unsupervised Learning of Image Transformations Roland Memisevic
• Learning a Nonlinear Embedding by Preserving Class Neighbourhood Structure
• Modeling pigeon behaviour using a Conditional Restricted Boltzmann Machine
• Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task
• Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine
• Multiple Relational Embedding Roland Memisevic
• Gatsby Computational Neuroscience Unit 17 Queen Square, London University College London WC1N 3AR, United Kingdom
• Stochastic Neighbor Embedding Geoffrey Hinton and Sam Roweis
• Adaptive Elastic Models for Hand-Printed Character Recognition
• TWO COLLABORATIVE FILTERING PROJECTS FOR CSC2515
• Cognitive Studies Program University of Sussex, Brighton
• Wormholes Improve Contrastive Divergence Geoffrey Hinton, Max Welling
• COMPUTER VISION AND IMAGE UNDERSTANDING Vol. 68, No. 1, October, pp. 120126, 1997
• Example learned topics and document model Train on 160K documents, subset of TREC AP corpus; use variational EM,
• Using Mixtures of Factor Analyzers for Segmentation and Pose Estimation
• timeseries distributed
• A NEW VIEW OF ICA G.E. Hinton, M. Welling, Y.W. Teh
• Multiple Relational Embedding Roland Memisevic
• Relative Density Nets: A New Way to Combine Backpropagation with HMM's
• What kind of a graphical model is the brain? Geoffrey E. Hinton
• MATLAB PrimerThird Edition Kermit Sigmon
• Spiking Boltzmann Machines Geo rey E. Hinton
• CSC2535 2011 ASSIGNMENT 2
• LEARNING DISTRIBUTED REPRESENTATIONS FOR STATISTICAL LANGUAGE MODELLING
• Analysis-by-Synthesis by Learning to Invert Generative Black Boxes
• LETTER Communicated by Dana Ballard Learning to Represent Spatial Transformations
• NeuralNetworks,Vol. 3, pp. 23-43, 1990 0893-6080/90 $3.00 ~ .00 Printed in the USA. All rights reserved. Copyright (re 1990 Pergamon Prcss plc
• To appear in: Advances in Neural Information Processing Systems 7, eds. Gerald Tesauro, David Touretzky and Todd Leen. Morgan Kaufmann, 1995
• CSC321: Introduction to Neural Networks and Machine Learning
• Dynamical Binary Latent Variable Models for 3D Human Pose Tracking Graham W. Taylor
• CSC321: 2011 Introduction to Neural Networks and
• Learning Sparse Topographic Representations with Products of Studentt Distributions
• Probabilities for machine learning Roland Memisevic
• A Neural Probabilistic Language Model Yoshua Bengio \Lambda , R ejean Ducharme and Pascal Vincent
• Sparse Overcomplete Energy-Based Models Energy-Based Models for Sparse Overcomplete
• To appear in: Advances in Neural Information Processing Systems 7, eds. Gerald Tesauro, David Touretzky and Todd Leen. Morgan Kaufmann, 1995
• CSC2515'02 1 Linear Algebra Review
• Introduction www.cs.toronto.edu/~hinton
• Gatsby Computational Neuroscience Unit 17 Queen Square, London University College London WC1N 3AR, United Kingdom
• perspective independently
• Deep Belief Networks for phone recognition Abdel-rahman Mohamed, George Dahl, and Geoffrey Hinton
• MATLAB Primer Third Edition
• Exponential Family Harmoniums with an Application to Information Retrieval
• Training Products of Experts by Minimizing Contrastive GCNU TR 2000-004
• TRAINING MANY SMALL HIDDEN MARKOV MODELS G. E. Hinton Gatsby Computational Neuroscience Unit, University College London,
• The EM Algorithm for Mixtures of Factor Analyzers Zoubin Ghahramani
• CSC321 Introduction to Neural Networks and Machine Learning
• CSC2515: Lecture 8 Continuous Latent Variables CSC2515 Fall 2007
• Department of Computer Science 6 King's College Rd, Toronto University of Toronto M5S 3G4, Canada
• Self Supervised Boosting Max Welling, Richard S. Zemel, and Geoffrey E. Hinton
• Introduction www.cs.toronto.edu/~hinton
• Classical and Bayesian Inference in Neuroimaging: Theory K. J. Friston, W. Penny, C. Phillips, S. Kiebel, G. Hinton, and J. Ashburner
• Implicit Mixtures of Restricted Boltzmann Machines Vinod Nair and Geoffrey Hinton
• Using mixtures of deformable models to capture variations in hand printed digits
• CSC2515: Lecture 6 Optimization CSC2515 Fall 2007
• CSC321: Introduction to Neural Networks and Machine Learning
• CSC321: 2011 Introduction to Neural Networks
• Transforming Autoencoders G. E. Hinton, A. Krizhevsky & S. D. Wang
• Extracting Distributed Representations of Concepts and Relations from Positive and Negative Propositions
• CSC 2535: 2011 Non-linear dimensionality reduction
• Generating Text with Recurrent Neural Networks Ilya Sutskever ILYA@CS.UTORONTO.CA
• DEEP BELIEF NETS FOR NATURAL LANGUAGE CALLROUTING Ruhi Sarikaya, Geoffrey E. Hinton, Bhuvana Ramabhadran