#1,145

Most Influential Person

Computer scientist and psychologist

Hinton has been called one of the “Godfathers of Artificial Intelligence” by media sources for his work on a neural network system known as “Deep Learning.” He divides his year between working for Google Brain, the influential AI group at Google, and as a professor of computer science at the University of Toronto in Canada.

Hinton, along with researchers David Rumelhart and Ronald Wilson, designed one of the key features in modern neural networks, a type of machine learning algorithm that learns from experience. In 1986, he published a description of using backpropagation to train neural networks on data, and this technique has become a lynchpin for all neural network successes to date. Hinton truly is one of the “godfathers” of AI, an honorific especially relevant today as major Web companies like Google, Facebook, Twitter and many others now use neural networks ubiquitously. At Google and the University of Toronto, Hinton focuses on Deep Learning systems, a type of neural networks that involves stacking multiple networks together to create powerful results, like learning to recognize faces and other objects in online photos. Self-driving cars also use Deep Learning systems for autonomous navigation.

Hinton was elected a Fellow of the Royal Society in 1998. With Yann LeCun and Yoshua Bengio, Hinton received the top prize in computer science, the Turing Award in 2018.

**Featured in Top Influential Computer Scientists Today**

According to Wikipedia, Geoffrey Everest Hinton is a British-Canadian cognitive psychologist and computer scientist, most noted for his work on artificial neural networks. Since 2013, he has divided his time working for Google and the University of Toronto. In 2017, he co-founded and became the Chief Scientific Advisor of the Vector Institute in Toronto.

- ImageNet classification with deep convolutional neural networks (68316)
- Dropout: a simple way to prevent neural networks from overfitting (24065)
- Learning internal representations by error propagation (18801)
- Visualizing Data using t-SNE (18218)
- Learning representations by back-propagating errors (18113)
- Reducing the Dimensionality of Data with Neural Networks (12909)
- A Fast Learning Algorithm for Deep Belief Nets (12268)
- Rectified Linear Units Improve Restricted Boltzmann Machines (11061)
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups (6807)
- Distilling the Knowledge in a Neural Network (6493)
- Speech recognition with deep recurrent neural networks (6190)
- Improving neural networks by preventing co-adaptation of feature detectors (5574)
- Training Products of Experts by Minimizing Contrastive Divergence (4235)
- Adaptive Mixtures of Local Experts (3799)
- Bayesian learning for neural networks (3611)
- A Learning Algorithm for Boltzmann Machines (3210)
- On the importance of initialization and momentum in deep learning (3062)
- Phoneme recognition using time-delay neural networks (2669)
- A View of the Em Algorithm that Justifies Incremental, Sparse, and other Variants (2547)
- A Practical Guide to Training Restricted Boltzmann Machines (2523)
- Layer Normalization (2293)
- Dynamic Routing Between Capsules (2216)
- Deep Neural Networks for Acoustic Modeling in Speech Recognition (2171)
- A Simple Framework for Contrastive Learning of Visual Representations (1942)
- Deep Boltzmann Machines (1896)
- Restricted Boltzmann machines for collaborative filtering (1660)
- Acoustic Modeling Using Deep Belief Networks (1585)
- Neighbourhood Components Analysis (1493)
- Connectionist Learning Procedures (1485)
- Learning representations by back-propagation errors, nature (1285)
- Learning and relearning in Boltzmann machines (1280)
- Stochastic Neighbor Embedding (1225)
- Unsupervised Learning (1218)
- Distributed Representations (1212)
- Semantic hashing (1190)
- How Learning Can Guide Evolution (1171)
- Generating Text with Recurrent Neural Networks (1131)
- The Helmholtz Machine (1120)
- Improving deep neural networks for LVCSR using rectified linear units and dropout (1060)
- The "wake-sleep" algorithm for unsupervised neural networks. (953)
- A Scalable Hierarchical Distributed Language Model (893)
- Learning distributed representations of concepts. (878)
- Parallel Models of Associative Memory (854)
- Autoencoders, Minimum Description Length and Helmholtz Free Energy (845)
- A general framework for parallel distributed processing (826)
- Learning multiple layers of representation (825)
- Keeping the neural networks simple by minimizing the description length of the weights (824)
- Grammar as a Foreign Language (801)
- Schemata and Sequential Thought Processes in PDP Models (785)
- Zero-shot Learning with Semantic Output Codes (770)
- New types of deep neural network learning for speech recognition and related applications: an overview (768)
- The EM algorithm for mixtures of factor analyzers (683)
- Transforming Auto-Encoders (680)
- On Contrastive Divergence Learning (667)
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer (644)
- A time-delay neural network architecture for isolated word recognition (629)
- Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems (607)
- Simplifying Neural Networks by Soft Weight-Sharing (603)
- Three new graphical models for statistical language modelling (583)
- The appeal of parallel distributed processing (578)
- Feudal Reinforcement Learning (575)
- Regularizing Neural Networks by Penalizing Confident Output Distributions (571)
- Parameter estimation for linear dynamical systems (568)
- Lesioning an attractor network: investigations of acquired dyslexia (546)
- Matrix capsules with EM routing (545)
- OPTIMAL PERCEPTUAL INFERENCE (544)
- A Simple Way to Initialize Recurrent Networks of Rectified Linear Units (516)
- Exponential Family Harmoniums with an Application to Information Retrieval (489)
- Replicated Softmax: an Undirected Topic Model (482)
- Evaluation of gaussian processes and other methods for non-linear regression (481)
- Learning representations of back-propagation errors (461)
- Learning a Nonlinear Embedding by Preserving Class Neighbourhood Structure (449)
- On rectified linear units for speech processing (447)
- Modeling Human Motion Using Binary Latent Variables (440)
- Modeling the manifolds of images of handwritten digits (415)
- SMEM Algorithm for Mixture Models (415)
- Learning to Detect Roads in High-Resolution Aerial Images (414)
- Glove-Talk: a neural network interface between a data-glove and a speech synthesizer (411)
- An Efficient Learning Procedure for Deep Boltzmann Machines (386)
- Experiments on Learning by Back Propagation. (382)
- Deep Belief Networks for phone recognition (380)
- When Does Label Smoothing Help? (379)
- Self-organizing neural network that discovers surfaces in random-dot stereograms (375)
- The Recurrent Temporal Restricted Boltzmann Machine (371)
- Factored conditional restricted Boltzmann Machines for modeling motion style (369)
- Mapping Part-Whole Hierarchies into Connectionist Networks (360)
- Big Self-Supervised Models are Strong Semi-Supervised Learners (352)
- 3D Object Recognition with Deep Belief Nets (349)
- Using very deep autoencoders for content-based image retrieval (344)
- Application of Deep Belief Networks for Natural Language Understanding (342)
- Parallel visual computation (341)
- Binary coding of speech spectrograms using a deep auto-encoder (328)
- NeuroAnimator: fast neural network emulation and control of physics-based models (321)
- Learning to combine foveal glimpses with a third-order Boltzmann machine (315)
- Variational Learning for Switching State-Space Models (314)
- Machine learning for aerial image labeling (311)
- Learning to Label Aerial Images from Noisy Data (311)
- Attend, Infer, Repeat: Fast Scene Understanding with Generative Models (309)
- Phone Recognition with the Mean-Covariance Restricted Boltzmann Machine (306)
- Deep belief networks (300)
- Distilling a Neural Network Into a Soft Decision Tree (300)
- Deep Belief Networks using discriminative features for phone recognition (291)
- Training recurrent neural networks (288)
- Understanding how Deep Belief Networks perform acoustic modelling (286)
- To recognize shapes, first learn to generate images. (283)
- Learning Generative Texture Models with extended Fields-of-Experts (274)
- Using fast weights to improve persistent contrastive divergence (274)
- Reducing the Dimensionality of Data with Neural (273)
- Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines (261)
- Generative models for discovering sparse distributed representations. (260)
- Modeling pixel means and covariances using factorized third-order boltzmann machines (255)
- An Alternative Model for Mixtures of Experts (250)
- Lookahead Optimizer: k steps forward, 1 step back (248)
- Learning Multilevel Distributed Representations for High-Dimensional Sequences (234)
- Global Coordination of Local Linear Models (233)
- Deep Learning-A Technology With the Potential to Transform Health Care. (232)
- Factored 3-Way Restricted Boltzmann Machines For Modeling Natural Images (229)
- Proceedings of the 1988 Connectionist Models Summer School (228)
- Products of experts (217)
- Massively Parallel Architectures for AI: NETL, Thistle, and Boltzmann Machines (210)
- A Parallel Computation that Assigns Canonical Object-Based Frames of Reference (208)
- Unsupervised Learning of Image Transformations (207)
- On deep generative models with applications to recognition (204)
- Symbols Among the Neurons: Details of a Connectionist Inference Architecture (202)
- Similarity of Neural Network Representations Revisited (201)
- Using Deep Belief Nets to Learn Covariance Kernels for Gaussian Processes (201)
- Learning Translation Invariant Recognition in Massively Parallel Networks (199)
- Large scale distributed neural network training through online distillation (195)
- A Distributed Connectionist Production System (190)
- Lesioning an attractor network: investigations of acquired dyslexia. (190)
- Using fast weights to deblur old memories (189)
- Learning a better representation of speech soundwaves using restricted boltzmann machines (188)
- Unsupervised learning : foundations of neural computation (185)
- Using Generative Models for Handwritten Digit Recognition (183)
- Visualizing non-metric similarities in multiple maps (179)
- Using Expectation-Maximization for Reinforcement Learning (176)
- Phoneme recognition: neural networks vs. hidden Markov models vs. hidden Markov models (173)
- Energy-Based Models for Sparse Overcomplete Representations (173)
- Distributed representations and nested compositional structure (172)
- Deterministic Boltzmann Learning Performs Steepest Descent in Weight-Space (163)
- A Distributed Connectionist Production System (158)
- Some Demonstrations of the Effects of Structural Descriptions in Mental Imagery (156)
- Transforming Autoencoders (154)
- Parallel computations for controlling an arm. (153)
- Robust Boltzmann Machines for recognition and denoising (152)
- Dynamical binary latent variable models for 3D human pose tracking (152)
- Learning Sparse Topographic Representations with Products of Student-t Distributions (149)
- Rate-coded Restricted Boltzmann Machines for Face Recognition (147)
- Glove-TalkII-a neural-network interface which maps gestures to parallel formant speech synthesizer controls (147)
- Learning Representations by Recirculation (146)
- Connectionist Architectures for Artificial Intelligence (145)
- Modeling image patches with a directed hierarchy of Markov random fields (140)
- A New Learning Algorithm for Mean Field Boltzmann Machines (137)
- Using Fast Weights to Attend to the Recent Past (137)
- 20 – CONNECTIONIST LEARNING PROCEDURES1 (136)
- Reinforcement Learning with Factored States and Actions (135)
- Groupoids associated with endomorphisms (135)
- Varieties of Helmholtz Machine (131)
- Preface to the Special Issue on Connectionist Symbol Processing (130)
- Recognizing Handwritten Digits Using Mixtures of Linear Models (128)
- A learning algorithm for Boltzmann machines (127)
- Adaptive Elastic Models for Hand-Printed Character Recognition (126)
- Learning sets of filters using back-propagation (125)
- Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures (125)
- Deep, Narrow Sigmoid Belief Networks Are Universal Approximators (123)
- Deep belief nets for natural language call-routing (123)
- Separating Figure from Ground with a Parallel Network (119)
- Two Distributed-State Models For Generating High-Dimensional Time Series (119)
- Topographic Product Models Applied to Natural Scene Statistics (117)
- Learning and Applying Contextual Constraints in Sentence Comprehension (116)
- A Better Way to Pretrain Deep Boltzmann Machines (115)
- Modeling Documents with Deep Boltzmann Machines (112)
- Unsupervised Discovery of Nonlinear Structure Using Contrastive Backpropagation (112)
- Scene-based and viewer-centered representations for comparing shapes (111)
- Shape Representation in Parallel Systems (110)
- Stacked Capsule Autoencoders (110)
- Conditional Restricted Boltzmann Machines for Structured Output Prediction (109)
- Evaluation of Adaptive Mixtures of Competing Experts (108)
- Who Said What: Modeling Individual Labelers Improves Classification (107)
- Phone recognition using Restricted Boltzmann Machines (107)
- Modeling documents with a Deep Boltzmann Machine (107)
- Discovering Binary Codes for Documents by Learning Deep Generative Models (106)
- Learning symmetry groups with hidden units: beyond the perceptron (102)
- Learning Distributed Representations of Concepts Using Linear Relational Embedding (99)
- Generating Facial Expressions with Deep Belief Nets (99)
- Visualizing Similarity Data with a Mixture of Maps (91)
- Switching State-Space Models (89)
- Learning to represent visual input (86)
- A comparison of statistical learning methods on the Gusto database. (85)
- Implicit Mixtures of Restricted Boltzmann Machines (85)
- A Mobile Robot That Learns Its Place (85)
- The shared views of four research groups ) (84)
- Relaxation and its role in vision (83)
- Gated Softmax Classification (82)
- Generative versus discriminative training of RBMs for classification of fMRI images (80)
- CvxNet: Learnable Convex Decomposition (77)
- Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition-' Washington , D . C . , June , 1983 OPTIMAL PERCEPTUAL INFERENCE (77)
- Split and Merge EM Algorithm for Improving Gaussian Mixture Density Estimates (77)
- A Desktop Input Device and Interface for Interactive 3D Character Animation (76)
- Variational Learning in Nonlinear Gaussian Belief Networks (75)
- The delve manual (75)
- Recognizing Hand-written Digits Using Hierarchical Products of Experts (75)
- Generating more realistic images using gated MRF's (74)
- Shape Recognition and Illusory Conjunctions (74)
- Deep Lambertian Networks (73)
- A soft decision-directed LMS algorithm for blind equalization (71)
- Where Do Features Come From? (67)
- Glove-TalkII: an adaptive gesture-to-formant interface (64)
- Mental simulation (64)
- Some Demonstrations of the Effects of Structural Descriptions in Mental Imagery (62)
- GTM through time (61)
- Keeping Neural Networks Simple (61)
- Modeling the joint density of two images under a variety of transformations (60)
- Does the Wake-sleep Algorithm Produce Good Density Estimators? (58)
- Deep Mixtures of Factor Analysers (58)
- Separating figure from ground with a Boltzmann machine (58)
- Building adaptive interfaces with neural networks: The glove-talk pilot study (58)
- Introduction to the Special Section on Deep Learning for Speech and Language Processing (57)
- Learning Mixture Models of Spatial Coherence (56)
- G-maximization: An unsupervised learning procedure for discovering regularities (56)
- Glove-TalkII: Mapping Hand Gestures to Speech Using Neural Networks (56)
- Modeling Natural Images Using Gated MRFs (55)
- Learning to Parse Images (52)
- What kind of graphical model is the brain? (51)
- Tensor Analyzers (51)
- Mean field networks that learn to discriminate temporally distorted strings (49)
- Glove-talk II - a neural-network interface which maps gestures to parallel formant speech synthesizer controls (48)
- A Hierarchical Community of Experts (47)
- Inferring Motor Programs from Images of Handwritten Digits (47)
- Self Supervised Boosting (46)
- Mundane Reasoning by Parallel Constraint Satisfaction (46)
- Analyzing and Improving Representations with the Soft Nearest Neighbor Loss (46)
- Multiple Relational Embedding (45)
- Neural Additive Models: Interpretable Machine Learning with Neural Nets (45)
- Learning Population Codes by Minimizing Description Length (44)
- Temporal-Kernel Recurrent Neural Networks (43)
- The Bootstrap Widrow-Hoff Rule as a Cluster-Formation Algorithm (42)
- Spiking Boltzmann Machines (42)
- Connectionist Symbol Processing (41)
- Comparing Classification Methods for Longitudinal fMRI Studies (40)
- Analysis-by-Synthesis by Learning to Invert Generative Black Boxes (40)
- Implementing Semantic Networks in Parallel Hardware (39)
- Untimed and Misrepresented: Connectionism and the Computer Metaphor Untimed and Misrepresented: Connectionism and the Computer Metaphor (38)
- Discovering Viewpoint-Invariant Relationships That Characterize Objects (38)
- Products of Hidden Markov Models (38)
- Dimensionality Reduction and Prior Knowledge in E-Set Recognition (38)
- Learning Sparse Networks Using Targeted Dropout (37)
- Local Physical Models for Interactive Character Animation (37)
- Imputer: Sequence Modelling via Imputation and Dynamic Programming (36)
- Generalized solenoids and C*-algebras (36)
- Bayesian networks for pattern classification, data compression, and channel coding (36)
- GENERALIZED CUNTZ-KRIEGER ALGEBRAS (36)
- Deep Belief Nets (36)
- Adaptive Soft Weight Tying using Gaussian Mixtures (35)
- Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions (34)
- Developing Population Codes by Minimizing Description Length (34)
- Learning Causally Linked Markov Random Fields (34)
- Reinforcement learning for factored markov decision processes (34)
- Hierarchical Non-linear Factor Analysis and Topographic Maps (33)
- Discovering Multiple Constraints that are Frequently Approximately Satisfied (29)
- Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task (29)
- Illustrative Language Understanding: Large-Scale Visual Grounding with Image Search (29)
- Using EM for Reinforcement Learning (29)
- A Mode-Hopping MCMC sampler (28)
- DARCCC: Detecting Adversaries by Reconstruction from Class Conditional Capsules (28)
- BoltzCONS: Dynamic Symbol Structures in a Connectionist Network (27)
- Fell bundles associated to groupoid morphisms (25)
- C^*-algebras associated with branched coverings (23)
- Using matrices to model symbolic relationship (23)
- TRAFFIC: Recognizing Objects Using Hierarchical Reference Frame Transformations (23)
- Cohomology of topological graphs and Cuntz-Pimsner algebras (22)
- A New View of ICA (22)
- The ups and downs of Hebb synapses. (22)
- Guest Editorial: Deep Learning (21)
- A simple algorithm that discovers efficient perceptual codes (21)
- Spatial coherence as an internal teacher for a neural network (20)
- GEMINI: Gradient Estimation Through Matrix Inversion After Noise Injection (20)
- Learning Hierarchical Structures with Linear Relational Embedding (20)
- Coaching variables for regression and classification (20)
- Improving a statistical language model through non-linear prediction (20)
- Combining deformable models and neural networks for handprinted digit recognition (19)
- How to represent part-whole hierarchies in a neural network (19)
- Autoregressive product of multi-frame predictions can improve the accuracy of hybrid models (19)
- Using Relaxation to find a Puppet (19)
- Using an autoencoder with deformable templates to discover features for automated speech recognition (18)
- CONTINUOUS GRAPHS AND C*-ALGEBRAS (18)
- Deterministic Boltzmann Learning in Networks with Asymmetric Connectivity (17)
- Extracting distributed representations of concepts and relations from positive and negative propositions (17)
- Wormholes Improve Contrastive Divergence (17)
- Directed Graphs (17)
- Efficient Stochastic Source Coding and an Application to a Bayesian Network Source Model (17)
- Group actions on topological graphs (16)
- A Practical Guide to Training (16)
- Instantiating Deformable Models with a Neural Net (16)
- Modeling pigeon behavior using a Conditional Restricted Boltzmann Machine (15)
- Using Pairs of Data-Points to Define Splits for Decision Trees (15)
- Imagery without arrays (14)
- Graphs of $C^*$-correspondences and Fell bundles (14)
- Learning in parallel networks: simulating learning in a probabilistic system (14)
- Free energy coding (14)
- C*-algebras associated with interval maps (14)
- Why the Islands Move (14)
- Hand-printed digit recognition using deformable models (13)
- Probabilistic sequential independent components analysis (13)
- Chapter IVb Some Computational Solutions to Bernstein's Problems (12)
- Improving dimensionality reduction with spectral gradient descent (12)
- A better way to learn features: technical perspective (12)
- Iterating the Pimsner construction (11)
- A new way to learn acoustic events (11)
- Dual Control (10)
- Speech recognition using time‐delay neural networks (10)
- Deep learning for AI (10)
- Bethe free energy and contrastive divergence approximations for undirected graphical models (10)
- Split and merge EM algorithm for improving Gaussian mixture density estimates (9)
- Minimizing Description Length in an Unsupervised Neural Network (9)
- Entropy estimates for some $\mathbf{C}^\ast$-endomorphisms (9)
- Discovering High Order Features with Mean Field Modules (9)
- Computation by neural networks (9)
- Deflecting Adversarial Attacks (9)
- Using a neural net to instantiate a deformable model (9)
- Products of Hidden Markov Models: It Takes N>1 to Tango (8)
- Subclass Distillation (8)
- An Efficient Learning Procedure for Deep (8)
- Representation and Control in Vision (7)
- Learning in massively parallel nets (7)
- Learning Distributed Representations by Mapping Concepts and Relations into a Linear Space (7)
- Intradural spinal hematoma in an infant with cystic fibrosis. (7)
- C∗-algebras and Fell bundles associated to a textile system (7)
- Inferring the meaning of direct perception (7)
- LEARNING SEMANTIC FEATURES (7)
- Efficient Parametric Projection Pursuit Density Estimation (7)
- Combining two methods of recognizing hand-printed digits (7)
- Fast Neural Network Emulation of Dynamical Systems for Computer Animation (7)
- Canonical Capsules: Unsupervised Capsules in Canonical Pose (6)
- Group actions on graphs and $C^*$-correspondences (6)
- Redes neuronales que aprenden de la experiencia (6)
- Modeling High-Dimensional Data by Combining Simple Experts (6)
- Training Products of Experts by Maximizing Contrastive Likelihood (6)
- Learning to Make Coherent Predictions in Domains with Discontinuities (5)
- Automated motif discovery in protein structure prediction (5)
- The Horizontal—Vertical Delusion (5)
- Learning Distributed Representations of Relational Data using Linear Relational Embedding (5)
- C*-algebras of commuting endomorphisms (5)
- Using Mixtures of Factor Analyzers for Segmentation and Pose Estimation (5)
- ATRIX CAPSULES WITH EM ROUTING (4)
- Teaching with Commentaries (4)
- Unsupervised part representation by Flow Capsules (4)
- TRAINING MANY SMALL HIDDEN MARKOV MODELS (4)
- Neural network architectures for artificial intelligence (4)
- Cerberus: A Multi-headed Derenderer (4)
- Boltzmann machine (4)
- Task and Object Learning in Visual Recognition (3)
- Machine learning for neuroscience (3)
- Groupoid actions on $C^*$-correspondences (3)
- Turn that frown upside-down! Inferring facial actions from pairs of images in a neurally plausible computational model (3)
- Bone mineral density and computer tomographic measurements in correlation with failure strength of equine metacarpal bones (3)
- How to generate realistic images using gated MRF ’ s (3)
- Cuntz-Pimsner Algebras of Group Representations (3)
- The Next Generation of Neural Networks (3)
- Unsupervised Learning: Foundations of Neural Computation--A Review (3)
- Decision Stump (3)
- Une nouvelle approche de la cognition : le connexionnisme (3)
- Relative Density Nets: A New Way to Combine Backpropagation with HMM's (3)
- Connectionist Models: Proceedings of the Summer School Held in San Diego, California on 1990 (3)
- Improving a statistical language model by modulating the effects of context words (3)
- Learnable Convex Decomposition (3)
- Fast Inference and Learning for Modeling Documents with a Deep Boltzmann Machine (2)
- Recursive Distributed Representations (2)
- Digital marionette: augmenting kinematics with physics for multi-track desktop performance animation (2)
- Non-linear dimensionality reduction using neural networks (2)
- Artificial Intelligence: Neural Networks (2)
- Residually AF embeddable C -algebras (2)
- Crossed products and twisted k-graph algebras (2)
- Workshop summary: Workshop on learning feature hierarchies (2)
- COHOMOLOGY OF TOPOLOGICAL GRAPHS (2)
- Cascaded redundancy reduction. (2)
- A PATH MODEL FOR CIRCLE ALGEBRAS (2)
- Scaling in a hierarchical unsupervised network (2)
- Deep Belief Nets (2)
- Unsupervised Object Discovery via Capsule Decoders (1)
- Number 20 (1)
- 0 Speeding up Backpropagation Algorithms (1)
- The Development of the Time-Delayed Neural Network Architecture (1)
- Three frames suffice (1)
- Learning in Massively Parallel Nets (Panel) (1)
- Developing a Mind: Learning in Humans, Animals, and Machines (1)
- Learning fast neural network emulators for physics-based models (1)
- Cascaded redundancy reduction (1)
- Using matrices to model symbolic relationships (1)
- Learning Pigeon Behaviour Using Binary Latent Variables (1)
- Pattern classification using a mixture of factor analyzers (1)
- On groupoids and $C^*$-algebras from self-similar actions. (1)
- COOPERATIVE : COMPUTATION (1)
- Using neural networks to learn intractable generative models (1)
- Approximate Contrastive Free Energies for Learning in Undirected Graphical Models (1)
- Models of human inference (1)
- Symmetries of the C⁎-algebra of a vector bundle (1)
- LEARNING IN BOLTZMANN MACHINES ' APPRENTISSAGE DANS LES MACHINES DE BOLTZMANN (1)
- Awards and Distinguished Papers (0)
- Boltzmann Machines (0)
- Modeling Semantic Similarities in Multiple Maps (0)
- Learning and Evaluaing Deep Bolztmann Machines (0)
- Developing Population Codes For Object Instantiation Parameters (0)
- Who’s Who in the Zoo: Defining Roles and Responsibilities of a Collaborative Health Care Team Abstract (0)
- Bellman Equation (0)
- GROUP ACTIONS ON GRAPHS (0)
- Thanks to our guest reviewers (0)
- Performance analysis of Neural Network Classifier for the Different Number of Hidden Units (0)
- nerative Models for andwritten Digit Recognition (0)
- Sustainability Attitudes of College Students as Future Business Leaders (0)
- Entropy of shifts on topological graph C ∗ -algebras (0)
- Simulación de lesiones cerebrales (0)
- Networks Reducing the Dimensionality of Data with Neural (0)
- Learning spatially coherent properties of the visual world in connectionist networks (0)
- Pacific Journal of Mathematics Generalized Solenoids and C*-algebras Valentin Deaconu (0)
- CSC 2535 2011 ASSIGNMENT 2 (0)
- Bias toward Higher Performance for the Decomposed Network. Whether a Decomposed Network Would Learn (0)
- November 21 , 2000 GCNU TR 2000 – 008 Products of Hidden Markov Models (0)
- The way things ought to be (0)
- Proceedings of the Connectionists Models Summer School Held in Pittsburgh, Pennsylvania on June 17-26, 1988 (0)
- Recluse Oil Field (0)
- Developing Population Codes For (0)
- Preventive psychotherapeutic measures for use with non-vocal clients. A case study. (0)
- Multifacility Location Problem using Scaled Conjugate Gradient Algorithm under Triangular Area Constraints (0)
- learning can then be used to fine-tune the CD solution . 1 ON CONTRASTIVE DIVERGENCE LEARNING (0)
- R M R S E N T a T I O N and Control in Vision ($5 ) (0)
- Scaling in a Hierarchical Unsupervised Network 1 (0)
- Higman-Thompson groups from self-similar groupoid actions (0)
- Detergent compositions containing percarbonate (0)
- Activity in Cognitive Elements 48 (0)
- Bias Variance Decomposition (0)
- Boltzmann Machines (0)
- Maximizing Mutual Information (0)
- Deep Belief Nets (0)
- Fast Neural Network Emulation and Control of Dynamical Systems (0)
- Mundane Reasoning by Settling on a Plausible Model (0)
- 認知・学習のコネクショニストモデル (機械は考えるか ) (0)
- Spiking Belief Networks (0)
- Embedding viaclustering: Using spectral information toguidedimensionality reduction (0)
- Detecting Handwritten Text from Forms using Deep Learning (0)
- In Memory of Ray Reiter (1939-2002) (0)
- Who Said What: Modelling Individual Labels Improves Classification (0)
- Group actions on graphs and Doplicher-Roberts algebras (0)
- is achieved. Prior to stabilization, neural networks do not jump around between points in activation space. Stabiliza-tion is the process whereby a network first generates a de-terminate activation pattern, and thereby arrives at a point in activation space (0)
- Artificial Intelligence Cytometer in Blood (0)
- 23 Generating Facial Expressions with Deep Belief Nets (0)
- C^*-algebras from k group representations (0)
- Report from Dagstuhl Seminar 14381 Neural-Symbolic Learning and Reasoning (0)
- A Bridge to Higher Mathematics (0)
- Inverting Generative Black Boxes with Breeder Learning (0)
- Proceedings of the 1990 Summer School on Connectionist models (0)
- A Bayesian Unsupervised Learning Algorithm that Scales (0)
- 7. Conclusion and Future Work Novel Objective Function for Improved Phoneme Recognition Using Time-delay Neural Networks. 5. Simulation Results (0)
- APPRENTISSAGE DANS LES MACHINES DE BOLTZMANN (0)
- Artificial Intelligence, Linguistics, Neuroscience, Philosophy, Psychology (0)
- Therapeutic difficulties in recurrent, multidrug-resistant epilepsy and vagal nerve stimulation, with recent traumatic brain complications needing iterative neurosurgical interventions (0)
- Cerberus : A Multiheaded Derenderer (0)
- Système et procédé permettant de paralléliser des réseaux neuronaux classiques (0)
- Système et méthode de résolution du problème de surapprentissage dans un réseau de neurones (0)
- The fundamental group of topological graphs and C -algebras (0)

This paper list is powered by the following services:

Geoffrey Hinton is affiliated with the following schools:

Computer Science

#37

World Rank

Psychology

#6707

World Rank

Mathematics

#7216

World Rank

Anthropology

#7462

World Rank

Physics

#9388

World Rank

Philosophy

#10457

World Rank

Engineering

#12003

World Rank

Biology

#12345

World Rank

Economics

#12621

World Rank

Chemistry

#27033

World Rank

Medical

#29391

World Rank

Communications

#29531

World Rank

This website uses cookies to enhance the user experience. Privacy Policy

Want to be an Academic Influence Insider?

Sign up to get the latest news, information, and rankings in our upcoming newsletter.