David Silver (programmer)

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search

Professor David Silver (dob c.1976) leads the reinforcement learning research group at DeepMind and was lead researcher on AlphaGo.

He graduated from Cambridge University in 1997 with the Addison-Wesley award, and befriended Demis Hassabis whilst there[1]. Subsequently, David co-founded the video games company Elixir Studios, where he was CTO and lead programmer, receiving several awards for technology and innovation.[2][3]

David returned to academia in 2004 at the University of Alberta to study for a PhD on reinforcement learning, where he co-introduced the algorithms used in the first master-level 9x9 Go programs.[4] David was awarded a Royal Society University Research Fellowship in 2011, and subsequently became a lecturer at University College London, where he is now a professor.[5] His lectures on Reinforcement Learning are available on YouTube[6]. David consulted for DeepMind from its inception, joining full-time in 2013.

His recent work has focused on combining reinforcement learning with deep learning, including a program that learns to play Atari games directly from pixels.[7] David led the AlphaGo project, culminating in the first program to defeat a top professional player in the full-size game of Go.[8] AlphaGo subsequently received an honorary 9 Dan Professional Certification; and won the Cannes Lion award for innovation.[9]. He then led development of AlphaZero, which used the same AI to learn to play Go from scratch (learning only by playing itself and not from human games) before learning to play chess and shogi in the same way, to higher levels than any other computer program[10].

David is among the most published members of staff at DeepMind and has an h-index of 40.[11]

References[edit]

  1. ^ http://uk.businessinsider.com/david-silver-the-unsung-hero-at-google-deepmind-2016-3
  2. ^ "David Silver: The unsung hero and intellectual powerhouse at Google DeepMind". Business Insider. Retrieved 2017-05-27. 
  3. ^ "What the AI Behind AlphaGo Can Teach Us About Being Human". Wired.com. Retrieved 17 May 2016. 
  4. ^ David, Silver,. "Reinforcement Learning and Simulation-Based Search in Computer Go". ERA. doi:10.7939/R39D8T. 
  5. ^ "CSML | David Silver". www.csml.ucl.ac.uk. Retrieved 2017-05-27. 
  6. ^ https://www.youtube.com/watch?v=2pWv7GOvuf0
  7. ^ Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David; Rusu, Andrei A.; Veness, Joel; Bellemare, Marc G.; Graves, Alex; Riedmiller, Martin; Fidjeland, Andreas K. (2015-02-26). "Human-level control through deep reinforcement learning". Nature. 518 (7540): 529–533. doi:10.1038/nature14236. ISSN 0028-0836. 
  8. ^ Silver, David; Huang, Aja; Maddison, Chris J.; Guez, Arthur; Sifre, Laurent; Driessche, George van den; Schrittwieser, Julian; Antonoglou, Ioannis; Panneershelvam, Veda; Lanctot, Marc; Dieleman, Sander; Grewe, Dominik; Nham, John; Kalchbrenner, Nal; Sutskever, Ilya; Lillicrap, Timothy; Leach, Madeleine; Kavukcuoglu, Koray; Graepel, Thore; Hassabis, Demis (28 January 2016). "Mastering the game of Go with deep neural networks and tree search". Nature. 529 (7587): 484–489. Bibcode:2016Natur.529..484S. doi:10.1038/nature16961. ISSN 0028-0836. PMID 26819042. Retrieved 10 December 2017. closed access publication – behind paywall
  9. ^ "Google DeepMind AlphaGo in U.K. Wins Innovation Grand Prix". Retrieved 2017-05-27. 
  10. ^ https://www.theguardian.com/technology/2017/dec/07/alphazero-google-deepmind-ai-beats-champion-program-teaching-itself-to-play-four-hours
  11. ^ "David Silver – Google Scholar Citations". Retrieved 30 August 2018.