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 Article
Learning Fast Optimizers for Contextual Stochastic Integer Programs
TL;DR: The constraints in the problem are known as non-anticipativity constraiants, since the enforce that x has to be chosen independent of the value of ω is unknown at the first stage.
Posted Content
Fast machine learning models of electronic and energetic properties consistently reach approximation errors better than DFT accuracy
Felix A. Faber,Luke Hutchinson,Huang Bing,Justin Gilmer,Samuel S. Schoenholz,George E. Dahl,Oriol Vinyals,Steven Kearnes,Patrick Riley,Anatole von Lilienfeld +9 more
TL;DR: Numerical evidence is presented that ML model predictions for all properties can reach an approximation error to DFT which is on par with chemical accuracy.
Proceedings ArticleDOI
Modulation spectrogram features for improved speaker diarization.
Oriol Vinyals,Gerald Friedland +1 more
TL;DR: Modulation spectrogram features in speaker diarization carry longer term characteristics of the acoustic signals than the widely used MFCCs, thus providing potential improvement by using both features in combination.
Proceedings ArticleDOI
A Hybrid Approach to Online Speaker Diarization
TL;DR: A hybrid approach that combines a traditional offline speaker diarization system (“who spoke when?”) with an online speaker identification system that allows a low-latency decision on the current speaker with an accuracy that is close to the underlying offline diarized system is presented.