G
George E. Dahl
Researcher at Google
Publications - 66
Citations - 36393
George E. Dahl is an academic researcher from Google. The author has contributed to research in topics: Artificial neural network & Hidden Markov model. The author has an hindex of 36, co-authored 56 publications receiving 29759 citations. Previous affiliations of George E. Dahl include Microsoft & University of Toronto.
Papers
More filters
The shared views of four research groups )
Geoffrey E. Hinton,Li Deng,Dong Yu,George E. Dahl,Abdelrahman Mohamed,Navdeep Jaitly,Andrew W. Senior,Vincent Vanhoucke,Patrick Nguyen,Tara N. Sainath,Brian Kingsbury +10 more
Proceedings Article
Training Restricted Boltzmann Machines on Word Observations
TL;DR: The success of this approach is demonstrated by training RBMs on hundreds of millions of word n-grams using larger vocabularies than previously feasible with RBMs and by using the learned features to improve performance on chunking and sentiment classification tasks, achieving state-of-the-art results on the latter.
Proceedings Article
Large scale distributed neural network training through online distillation
Rohan Anil,Gabriel Pereyra,Alexandre Passos,Róbert Ormándi,George E. Dahl,Geoffrey E. Hinton +5 more
TL;DR: In this paper, the authors explore a variant of distillation which is relatively straightforward to use as it does not require a complicated multi-stage setup or many new hyperparameters.
Posted Content
Training Restricted Boltzmann Machines on Word Observations
TL;DR: This paper used Markov chain Monte Carlo (MCMC) operators on the visible units, yielding updates with computational complexity independent of K. They demonstrate the success of their approach by training RBMs on hundreds of millions of word n-grams using larger vocabularies than previously feasible.
Journal Article
Measuring the Effects of Data Parallelism on Neural Network Training
Christopher J. Shallue,Jaehoon Lee,Joseph M. Antognini,Jascha Sohl-Dickstein,Roy Frostig,George E. Dahl +5 more
TL;DR: In this paper, the effects of increasing the batch size on training time of neural networks have been investigated, as measured by the number of steps necessary to reach a goal out-of-sample error.