O
Oriol Vinyals
Researcher at Google
Publications - 218
Citations - 121048
Oriol Vinyals is an academic researcher from Google. The author has contributed to research in topics: Artificial neural network & Reinforcement learning. The author has an hindex of 84, co-authored 200 publications receiving 82365 citations. Previous affiliations of Oriol Vinyals include University of California, San Diego & University of California, Berkeley.
Papers
More filters
Proceedings ArticleDOI
Discriminative pronounciation learning using phonetic decoder and minimum-classification-error criterion
TL;DR: The new discriminative pronunciation learning technique overcomes the limitation of the traditional ways of introducing alternative pronunciations that often enlarge confusability across different lexical items and is used to improve the pronunciation-modeling component of a speech recognition system designed for mobile voice search.
Posted Content
Metacontrol for Adaptive Imagination-Based Optimization
Jessica B. Hamrick,Andrew J. Ballard,Razvan Pascanu,Oriol Vinyals,Nicolas Heess,Peter W. Battaglia +5 more
TL;DR: In this paper, the authors introduce a metacontroller which learns to optimize a sequence of internal simulations over predictive models of the world in order to construct a more informed, and more economical, solution.
Proceedings Article
Pointer Graph Networks
Petar Veličković,Lars Buesing,Matthew C. Overlan,Razvan Pascanu,Oriol Vinyals,Charles Blundell +5 more
TL;DR: Pointer Graph Networks (PGNs) are introduced which augment sets or graphs with additional inferred edges for improved model expressivity and can learn parallelisable variants of pointer-based data structures, namely disjoint set unions and link/cut trees.
Proceedings Article
Metacontrol for Adaptive Imagination-Based Optimization
Jessica B. Hamrick,Andrew J. Ballard,Razvan Pascanu,Oriol Vinyals,Nicolas Heess,Peter W. Battaglia +5 more
TL;DR: This work introduces a metacontroller which learns to optimize a sequence of "imagined" internal simulations over predictive models of the world in order to construct a more informed, and more economical, solution.
Proceedings Article
Learning Implicit Generative Models with the Method of Learned Moments
TL;DR: This paper proposed a method of moments (MoM) algorithm for training large-scale implicit generative models, which defines the moments as the hidden units and the gradient of the network's output with respect to its parameters.