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
Journal ArticleDOI
Speech recognition using time‐delay neural networks
TL;DR: A time‐delay neural network approach to speech recognition that “invented” well‐known acoustic‐phonetic features as useful abstractions and recognizes voiced stops extracted from varying phonetic contexts at an error rate four times lower than the best of the authors' HMMs.
Posted Content
Cerberus: A Multi-headed Derenderer.
TL;DR: C Cerberus, the multi-headed derenderer, outperforms previous methods for extracting 3D parts from single images without part annotations, and it does quite well at extracting natural parts of human figures.
Proceedings Article
Products of Hidden Markov Models: it takes N>1 to tango
TL;DR: The authors demonstrate how the partition function can be estimated reliably via Annealed Importance Sampling (AIS) using contrastive divergence learning on rainfall data and data captured from pairs of people dancing, and suggest that advances in learning and evaluation for undirected graphical models and recent increases in available computing power make PoHMMs worth considering for complex time series modeling tasks.
Bethe free energy and contrastive divergence approximations for undirected graphical models
Geoffrey E. Hinton,Yee Whye Teh +1 more
TL;DR: This thesis develops RBMrate, a model for discretized continuous-valued data and describes sparse and over-complete representations of data where the inference process is trivial since it is simply an EBM, and contributes a theory relating belief propagation and iterative scaling to the Bethe free energy approximations.