doi.bio/koray_kavukcuoglu

Koray Kavukcuoglu

Koray Kavukcuoglu is a Turkish researcher in machine learning and artificial intelligence. He currently serves as the Vice President of Research at DeepMind, where he previously worked as a research scientist and led the deep learning team.

Education

Kavukcuoglu holds a Bachelor's and Master's degree in Aerospace Engineering from the Middle East Technical University in Ankara, Turkey. He then went on to pursue a PhD in Computer Science from New York University, graduating in 2010. During his doctoral studies, he worked in Yann LeCun's group at the Computational and Biological Learning Lab, focusing on unsupervised learning of feature extractors and multi-stage architectures for object recognition.

Career

Prior to joining DeepMind, Kavukcuoglu was a research staff member at NEC Labs America in the machine learning department. He has also contributed significantly to the field of machine learning through his involvement with Torch5, a machine learning library, and its subsequent versions. Along with Ronan Collobert and Clément Farabet, he is a developer of Torch5.

Publications

Kavukcuoglu has numerous publications in the field of machine learning, including:

• Implementing Neural Networks Efficiently (2012) - Co-authored with Ronan Collobert and Clément Farabet, this chapter in the book "Neural Networks: Tricks of the Trade" focuses on efficient implementation of neural networks.
• Playing Atari with Deep Reinforcement Learning (2013) - This paper, published on arXiv, details the use of deep reinforcement learning to train an agent to play Atari games.
• Human-level control through deep reinforcement learning (2015) - Published in Nature, this paper demonstrates how deep reinforcement learning can be used to achieve human-level performance in a range of tasks.
• Natural Neural Networks (2015) - This paper, co-authored with Guillaume Desjardins, Karen Simonyan, and Razvan Pascanu, explores the idea of natural neural networks and their potential applications.
• WaveNet: A Generative Model for Raw Audio (2016) - In this paper published on arXiv, Kavukcuoglu and his colleagues propose WaveNet, a generative model for raw audio that can generate speech and music with unprecedented quality.
• Asynchronous Methods for Deep Reinforcement Learning (2016) - This paper explores asynchronous methods for deep reinforcement learning, which can help improve the efficiency of training and enable agents to learn more complex tasks.

Google Scholar

koray kavukcuoglu

DeepMind

http://koray.kavukcuoglu.org/

Human-level control through deep reinforcement learning V Mnih, K Kavukcuoglu, D Silver, AA Rusu, J Veness, MG Bellemare, … nature 518 (7540), 529-533, 2015 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:dhFuZR0502QC

Highly accurate protein structure prediction with AlphaFold J Jumper, R Evans, A Pritzel, T Green, M Figurnov, O Ronneberger, … nature 596 (7873), 583-589, 2021 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:i_7YvbSbtFEC

Mastering the game of Go with deep neural networks and tree search D Silver, A Huang, CJ Maddison, A Guez, L Sifre, G Van Den Driessche, … nature 529 (7587), 484-489, 2016 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:yY3RG6sOEgwC

Playing atari with deep reinforcement learning V Mnih, K Kavukcuoglu, D Silver, A Graves, I Antonoglou, D Wierstra, … arXiv preprint arXiv:1312.5602, 2013 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:M3ejUd6NZC8C

Asynchronous methods for deep reinforcement learning V Mnih, AP Badia, M Mirza, A Graves, T Lillicrap, T Harley, D Silver, … International conference on machine learning, 1928-1937, 2016 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:wSy_KLzO7YEC

Natural language processing (almost) from scratch R Collobert, J Weston, L Bottou, M Karlen, K Kavukcuoglu, P Kuksa Journal of machine learning research 12, 2493− 2537, 2011 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:IjCSPb-OGe4C

Spatial transformer networks M Jaderberg, K Simonyan, A Zisserman Advances in neural information processing systems 28, 2015 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:IWHjjKOFINEC

Matching networks for one shot learning O Vinyals, C Blundell, T Lillicrap, D Wierstra Advances in neural information processing systems 29, 2016 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:iyewoVqAXLQC

Bootstrap your own latent-a new approach to self-supervised learning JB Grill, F Strub, F Altché, C Tallec, P Richemond, E Buchatskaya, … Advances in neural information processing systems 33, 21271-21284, 2020 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:uUvzmPk0f8oC

Wavenet: A generative model for raw audio A Van Den Oord, S Dieleman, H Zen, K Simonyan, O Vinyals, A Graves, … arXiv preprint arXiv:1609.03499 12, 2016 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:Vztgr1qGG8IC

Recurrent models of visual attention V Mnih, N Heess, A Graves Advances in neural information processing systems 27, 2014 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:9ZlFYXVOiuMC

Grandmaster level in StarCraft II using multi-agent reinforcement learning O Vinyals, I Babuschkin, WM Czarnecki, M Mathieu, A Dudzik, J Chung, … nature 575 (7782), 350-354, 2019 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:PuOEWVtPfzwC

Weight uncertainty in neural network C Blundell, J Cornebise, K Kavukcuoglu, D Wierstra International conference on machine learning, 1613-1622, 2015 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:ZeXyd9-uunAC

Neural discrete representation learning A Van Den Oord, O Vinyals Advances in neural information processing systems 30, 2017 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:QoJ_w57xiyAC

Improved protein structure prediction using potentials from deep learning AW Senior, R Evans, J Jumper, J Kirkpatrick, L Sifre, T Green, C Qin, … Nature 577 (7792), 706-710, 2020 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:60iIaj97TE0C

What is the best multi-stage architecture for object recognition? K Jarrett, K Kavukcuoglu, MA Ranzato, Y LeCun 2009 IEEE 12th international conference on computer vision, 2146-2153, 2009 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:u5HHmVD_uO8C

Convolutional networks and applications in vision Y LeCun, K Kavukcuoglu, C Farabet Proceedings of 2010 IEEE international symposium on circuits and systems …, 2010 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:qjMakFHDy7sC

Progressive neural networks AA Rusu, NC Rabinowitz, G Desjardins, H Soyer, J Kirkpatrick, … arXiv preprint arXiv:1606.04671, 2016 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:ji7lAbPyDbYC

Pixel recurrent neural networks A Van Den Oord, N Kalchbrenner, K Kavukcuoglu International conference on machine learning, 1747-1756, 2016 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:wUn16MOA3RoC

Conditional image generation with pixelcnn decoders A Van den Oord, N Kalchbrenner, L Espeholt, O Vinyals, A Graves Advances in neural information processing systems 29, 2016 Link: https://scholar.google.com/citations?viewop=viewcitation&hl=en&user=sGFyDIUAAAAJ&citationforview=sGFyDIUAAAAJ:4e5Qn2KL_jwC

Co-authors

David Silver googlescholarauthorid davidsilver.md:-8DNE4UAAAAJ

Alex Graves googlescholarauthorid alexgraves.md:DaFHynwAAAAJ

Volodymyr Mnih googlescholarauthorid volodymyrmnih.md:rLdfJ1gAAAAJ

Yann LeCun googlescholarauthorid yannlecun.md:WLN3QrAAAAAJ

Ronan Collobert googlescholarauthorid ronancollobert.md:32w7x1cAAAAJ

Pierre Sermanet googlescholarauthorid pierresermanet.md:0nPi5YYAAAAJ

Pavel P. Kuksa googlescholarauthorid pavelp._kuksa.md:EgVWuhAAAAAJ

Marc'Aurelio Ranzato googlescholarauthorid marc'aurelioranzato.md:NbXF7T8AAAAJ

Clement Farabet googlescholarauthorid clementfarabet.md:u3u16tgAAAAJ

Y-Lan Boureau googlescholarauthorid y-lanboureau.md:GfcBlpUAAAAJ

Demis Hassabis googlescholarauthorid demishassabis.md:dYpPMQEAAAAJ