K
Koray Kavukcuoglu
Researcher at Google
Publications - 129
Citations - 142028
Koray Kavukcuoglu 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 124 publications receiving 98426 citations. Previous affiliations of Koray Kavukcuoglu include Courant Institute of Mathematical Sciences & Princeton University.
Papers
More filters
Posted Content
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
Jean-Bastien Grill,Florian Strub,Florent Altché,Corentin Tallec,Pierre H. Richemond,Elena Buchatskaya,Carl Doersch,Bernardo Avila Pires,Zhaohan Daniel Guo,Mohammad Gheshlaghi Azar,Bilal Piot,Koray Kavukcuoglu,Rémi Munos,Michal Valko +13 more
TL;DR: This work introduces Bootstrap Your Own Latent (BYOL), a new approach to self-supervised image representation learning that performs on par or better than the current state of the art on both transfer and semi- supervised benchmarks.
Journal ArticleDOI
Grandmaster level in StarCraft II using multi-agent reinforcement learning.
Oriol Vinyals,Igor Babuschkin,Wojciech Marian Czarnecki,Michael Mathieu,Andrew Dudzik,Junyoung Chung,David H. Choi,Richard E. Powell,Timo Ewalds,Petko Georgiev,Junhyuk Oh,Dan Horgan,Manuel Kroiss,Ivo Danihelka,Aja Huang,Laurent Sifre,Trevor Cai,John P. Agapiou,Max Jaderberg,Alexander Vezhnevets,Rémi Leblond,Tobias Pohlen,Valentin Dalibard,David Budden,Yury Sulsky,James Molloy,Tom Le Paine,Caglar Gulcehre,Ziyu Wang,Tobias Pfaff,Yuhuai Wu,Roman Ring,Dani Yogatama,Dario Wünsch,Katrina McKinney,Oliver Smith,Tom Schaul,Timothy P. Lillicrap,Koray Kavukcuoglu,Demis Hassabis,Chris Apps,David Silver +41 more
TL;DR: The agent, AlphaStar, is evaluated, which uses a multi-agent reinforcement learning algorithm and has reached Grandmaster level, ranking among the top 0.2% of human players for the real-time strategy game StarCraft II.
Proceedings ArticleDOI
What is the best multi-stage architecture for object recognition?
TL;DR: It is shown that using non-linearities that include rectification and local contrast normalization is the single most important ingredient for good accuracy on object recognition benchmarks and that two stages of feature extraction yield better accuracy than one.
Posted Content
Recurrent Models of Visual Attention
TL;DR: In this article, a recurrent neural network (RNN) model is proposed to extract information from an image or video by adaptively selecting a sequence of regions or locations and only processing the selected regions at high resolution.
Journal ArticleDOI
Improved protein structure prediction using potentials from deep learning
Andrew W. Senior,Richard Evans,John M. Jumper,James Kirkpatrick,Laurent Sifre,Tim Green,Chongli Qin,Augustin Žídek,Alexander Nelson,Alex Bridgland,Hugo Penedones,Stig Petersen,Karen Simonyan,Steve Crossan,Pushmeet Kohli,David T. Jones,David T. Jones,David Silver,Koray Kavukcuoglu,Demis Hassabis +19 more
TL;DR: It is shown that a neural network can be trained to make accurate predictions of the distances between pairs of residues, which convey more information about the structure than contact predictions, and the resulting potential can be optimized by a simple gradient descent algorithm to generate structures without complex sampling procedures.