David Silver (computer scientist)

David Silver FRS (born 1976) is a principal research scientist at Google DeepMind and a professor at University College London. He has led research on reinforcement learning with AlphaGo, AlphaZero and co-lead on AlphaStar.[1][2]

David Silver

FRS
Born1976 (age 46–47)
Alma materUniversity of Cambridge (BA)
University of Alberta (PhD)
Known forAlphaGo
AlphaZero
AlphaStar
AwardsRoyal Society University Research Fellowship (2011)
ACM Prize in Computing (2019)
Scientific career
FieldsArtificial intelligence
Machine learning
Reinforcement learning
Planning
Computer Games[1]
InstitutionsGoogle Deepmind
University College London
Elixir Studios
ThesisReinforcement learning and simulation-based search in computer Go (2009)
Websitewww.davidsilver.uk

Education

He studied at Christ's College, Cambridge,[3] graduating in 1997 with the Addison-Wesley award, and having befriended Demis Hassabis whilst at Cambridge.[4] Silver returned to academia in 2004 at the University of Alberta to study for a PhD on reinforcement learning,[5] where he co-introduced the algorithms used in the first master-level 9×9 Go programs and graduated in 2009.[6][7] His version of program MoGo (co-authored with Sylvain Gelly) was one of the strongest Go programs as of 2009.[8]

Career and research

After graduating from university, Silver co-founded the video games company Elixir Studios, where he was CTO and lead programmer, receiving several awards for technology and innovation.[4][9]

Silver was awarded a Royal Society University Research Fellowship in 2011, and subsequently became a lecturer at University College London.[10] His lectures on Reinforcement Learning are available on YouTube.[11] Silver consulted for Google 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.[12] Silver led the AlphaGo project, culminating in the first program to defeat a top professional player in the full-size game of Go.[13] AlphaGo subsequently received an honorary 9 Dan Professional Certification; and won the Cannes Lion award for innovation.[14] 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.

Silver is among the most published members of staff at Google DeepMind, with over 130,000 citations and has an h-index of 78 according to Google scholar.[1]

Awards and honours

Silver was awarded the 2019 ACM Prize in Computing for breakthrough advances in computer game-playing.[15]

In 2021, Silver was elected Fellow of the Royal Society (FRS) for his contributions to Deep Q-Networks and AlphaGo.[16]

References
  1. David Silver publications indexed by Google Scholar
  2. Oriol Vinyals; Igor Babuschkin; Wojciech M Czarnecki; et al. (30 October 2019). "Grandmaster level in StarCraft II using multi-agent reinforcement learning". Nature. 575 (7782): 350–354. doi:10.1038/S41586-019-1724-Z. ISSN 1476-4687. PMID 31666705. Wikidata Q72988805.
  3. The Cambridge University List of Members up to 31 July 1998
  4. Shead, Sam. "David Silver: The unsung hero and intellectual powerhouse at Google DeepMind". businessinsider.com. Retrieved 26 September 2020.
  5. David Silver at the Mathematics Genealogy Project
  6. Silver, David (2009). Reinforcement Learning and Simulation-Based Search in Computer Go. ualberta.ca (PhD thesis). University of Alberta. doi:10.7939/R39D8T. OCLC 575410609.
  7. Sylvain Gelly; David Silver (2008). "Achieving Master Level Play in 9 × 9 Computer Go" (PDF). Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence.
  8. Stuart J. Russell; Peter Norvig (2009). Artificial Intelligence: A Modern Approach (3rd ed.). Prentice Hall.
  9. "What the AI Behind AlphaGo Can Teach Us About Being Human". Wired.com. Retrieved 17 May 2016.
  10. "CSML | David Silver". ucl.ac.uk. Archived from the original on 24 April 2021. Retrieved 27 May 2017.
  11. "RL Course by David Silver - Lecture 1: Introduction to Reinforcement Learning". 13 May 2015 – via YouTube.
  12. Volodymyr Mnih; Koray Kavukcuoglu; David Silver; et al. (25 February 2015). "Human-level control through deep reinforcement learning". Nature. 518 (7540): 529–533. doi:10.1038/NATURE14236. ISSN 1476-4687. PMID 25719670. Wikidata Q27907579.
  13. David Silver; Aja Huang; Chris J. Maddison; et al. (27 January 2016). "Mastering the game of Go with deep neural networks and tree search". Nature. 529 (7587): 484–489. doi:10.1038/NATURE16961. ISSN 1476-4687. PMID 26819042. Wikidata Q28005460.
  14. "Google DeepMind AlphaGo in U.K. Wins Innovation Grand Prix". Retrieved 27 May 2017.
  15. Ormond, Jim. "ACM Prize in Computing Awarded to AlphaGo Developer: David Silver Recognized for Breakthrough Advances in Computer Game-Playing". acm.org. Retrieved 2 April 2020.
  16. "Royal Society elects outstanding new Fellows and Foreign Members". royalsociety.org. Retrieved 8 June 2021.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.