G
Geoffrey E. Hinton
Researcher at Google
Publications - 426
Citations - 501778
Geoffrey E. Hinton is an academic researcher from Google. The author has contributed to research in topics: Artificial neural network & Generative model. The author has an hindex of 157, co-authored 414 publications receiving 409047 citations. Previous affiliations of Geoffrey E. Hinton include Canadian Institute for Advanced Research & Max Planck Society.
Papers
More filters
Proceedings ArticleDOI
Extracting distributed representations of concepts and relations from positive and negative propositions
TL;DR: This paper presents results in two simple domains, which show that learning leads to good generalization in linear relational embedding and an extended formulation of LRE that solves both these problems.
Journal ArticleDOI
Instantiating deformable models with a neural net
TL;DR: By training a neural network to predict how a deformable model should be instantiated from an input image, improved starting points can be obtained and the search time can be significantly reduced without compromising recognition performance.
Proceedings Article
Wormholes Improve Contrastive Divergence
TL;DR: This work shows how to improve brief MCMC by allowing long-range moves that are suggested by the data distribution, if the model is approximately correct, and these long- range moves have a reasonable acceptance rate.
Patent
System and method for generating training cases for image classification
TL;DR: In this article, an image processing module performs color-space deformation on each pixel of the existing training image and then associates the classification to the color space deformed training image, which may be applied to increase the size of a training set for training a neural network.
Combining deformable models and neural networks for handprinted digit recognition
TL;DR: A method for recognizing isolated handprinted digits using trainable deformable models that can handle arbitrary scalings, translations and a limited degree of image rotation and can be significantly speeded up by using a neural net to provide better starting points for the search.