Jump to content

Peter Dayan: Difference between revisions

Edit links
From Wikipedia, the free encyclopedia
Browse history interactively
← Previous editNext edit →
Content deleted Content added
VisualWikitext
Added free to read link in citations with OAbot #oabot
Citation bot (talk | contribs)
Bots
5,352,496 edits
m Alter: issue, journal. Add: pmid, doi, issue, oclc. Removed URL that duplicated unique identifier. Removed parameters. Formatted dashes. | You can use this bot yourself. Report bugs here.| Activated by User:Nemo bis | via #UCB_webform
Line 48: Line 48:
| footnotes =
| footnotes =
}}
}}
'''Peter Samuel Dayan''' {{post-nominals|country=GBR|FRS}} is director at the [[Max Planck Institute for Biological Cybernetics]] in [[Tübingen]], Germany. He is co-author of ''Theoretical Neuroscience'',<ref>{{Cite book|url=https://www.worldcat.org/title/theoretical-neuroscience-computational-and-mathematical-modeling-of-neural-systems/oclc/952504127|title=Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems|last=Dayan|first=Peter|last2=Abbott|first2=Laurence|date=2014|publisher=MIT Press|isbn=9780262541855|location=Cambridge|language=English}}</ref> an influential textbook on [[computational neuroscience]]. He is known for applying [[bayesian method]]s from [[machine learning]] and [[artificial intelligence]] to understand neural function and is particularly recognized for relating [[neurotransmitter]] levels to prediction errors and Bayesian uncertainties.<ref name="SchultzDayan1997">{{cite journal|last1=Schultz|first1=W.|last2=Dayan|first2=P.|last3=Montague|first3=P. R.|title=A Neural Substrate of Prediction and Reward|journal=Science|volume=275|issue=5306|year=1997|pages=1593–1599|issn=0036-8075|doi=10.1126/science.275.5306.1593|pmid=9054347|url=http://www.cs.utexas.edu/~dana/Reward.pdf}} {{closed access}}</ref> He has pioneered the field of [[reinforcement learning]] (RL) where he helped develop the [[Q-learning]] algorithm, and made contributions to [[unsupervised learning]], including the [[wake-sleep algorithm]] for [[neural network]]s and the [[Helmholtz machine]].<ref name=q>{{cite journal|last1=Watkins|first1=Christopher J. C. H.|last2=Dayan|first2=Peter|title=Q-learning|journal=Machine Learning|volume=8|issue=3-4|year=1992|pages=279–292|issn=0885-6125|doi=10.1007/BF00992698}}</ref><ref name="Dayan1992">{{cite journal|last1=Dayan|first1=Peter|journal=Machine Learning|title=The convergence of TD (λ) for general λ|volume=8|issue=3/4|year=1992|pages=341–362|issn=08856125|doi=10.1023/A:1022632907294}}</ref><ref>{{Cite journal|title = The helmholtz machine.|journal = Neural computation|date = 1995|pages = 889-904|volume = 7|first = Dayan|last = Peter|authorlink1=Peter Dayan|first2 = Geoffrey E.|last2 = Hinton|authorlink2=Geoffrey Hinton|first3 = Radford M.|last3 = Neal|authorlink3=Radford M. Neal|first4 = Richard S.|last4 = Zemel|authorlink4=Richard Zemel}} {{closed access}}</ref>
'''Peter Samuel Dayan''' {{post-nominals|country=GBR|FRS}} is director at the [[Max Planck Institute for Biological Cybernetics]] in [[Tübingen]], Germany. He is co-author of ''Theoretical Neuroscience'',<ref>{{Cite book|title=Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems|last=Dayan|first=Peter|last2=Abbott|first2=Laurence|date=2014|publisher=MIT Press|isbn=9780262541855|location=Cambridge|language=English|oclc = 952504127}}</ref> an influential textbook on [[computational neuroscience]]. He is known for applying [[bayesian method]]s from [[machine learning]] and [[artificial intelligence]] to understand neural function and is particularly recognized for relating [[neurotransmitter]] levels to prediction errors and Bayesian uncertainties.<ref name="SchultzDayan1997">{{cite journal|last1=Schultz|first1=W.|last2=Dayan|first2=P.|last3=Montague|first3=P. R.|title=A Neural Substrate of Prediction and Reward|journal=Science|volume=275|issue=5306|year=1997|pages=1593–1599|issn=0036-8075|doi=10.1126/science.275.5306.1593|pmid=9054347|url=http://www.cs.utexas.edu/~dana/Reward.pdf}} {{closed access}}</ref> He has pioneered the field of [[reinforcement learning]] (RL) where he helped develop the [[Q-learning]] algorithm, and made contributions to [[unsupervised learning]], including the [[wake-sleep algorithm]] for [[neural network]]s and the [[Helmholtz machine]].<ref name=q>{{cite journal|last1=Watkins|first1=Christopher J. C. H.|last2=Dayan|first2=Peter|title=Q-learning|journal=Machine Learning|volume=8|issue=3–4|year=1992|pages=279–292|issn=0885-6125|doi=10.1007/BF00992698}}</ref><ref name="Dayan1992">{{cite journal|last1=Dayan|first1=Peter|journal=Machine Learning|title=The convergence of TD (λ) for general λ|volume=8|issue=3/4|year=1992|pages=341–362|issn=08856125|doi=10.1023/A:1022632907294}}</ref><ref>{{Cite journal|title = The helmholtz machine.|journal = Neural Computation|date = 1995|pages = 889–904|volume = 7|issue = 5|first = Dayan|last = Peter|authorlink1=Peter Dayan|first2 = Geoffrey E.|last2 = Hinton|authorlink2=Geoffrey Hinton|first3 = Radford M.|last3 = Neal|authorlink3=Radford M. Neal|first4 = Richard S.|last4 = Zemel|authorlink4=Richard Zemel|doi = 10.1162/neco.1995.7.5.889|pmid = 7584891}} {{closed access}}</ref>


==Education==
==Education==
Dayan studied mathematics at the [[University of Cambridge]] and then continued for a [[PhD]] in [[artificial intelligence]] at the [[University of Edinburgh School of Informatics]] on statistical learning <ref name=phd>{{Cite thesis|last=Dayan|first=Peter Samuel|degree=PhD|date=1991|title=Reinforcing connectionism: learning the statistical way|url=https://www.era.lib.ed.ac.uk/handle/1842/14754|website=lib.ed.ac.uk|hdl=1842/14754|language=en|id={{EThOS|uk.bl.ethos.649240}}}} {{free access}}</ref> supervised by [[d:Q54978760|David Willshaw]] and [[David Wallace (physicist)|David Wallace]], focusing on [[Association (psychology)|associative]] [[memory]] and [[reinforcement learning]].<ref name=phd/>
Dayan studied mathematics at the [[University of Cambridge]] and then continued for a [[PhD]] in [[artificial intelligence]] at the [[University of Edinburgh School of Informatics]] on statistical learning <ref name=phd>{{Cite thesis|last=Dayan|first=Peter Samuel|degree=PhD|date=1991|title=Reinforcing connectionism: learning the statistical way|hdl=1842/14754|language=en|id={{EThOS|uk.bl.ethos.649240}}}} {{free access}}</ref> supervised by [[d:Q54978760|David Willshaw]] and [[David Wallace (physicist)|David Wallace]], focusing on [[Association (psychology)|associative]] [[memory]] and [[reinforcement learning]].<ref name=phd/>


==Career and research==
==Career and research==

Revision as of 09:18, 11 December 2019

Peter Dayan
FRS
Peter Dayan at the Royal Society admissions day in London, July 2018
Born
Peter Samuel Dayan

1965 (age 58–59)
Alma materUniversity of Cambridge (BA)
University of Edinburgh (PhD)
Known forQ-learning
AwardsRumelhart Prize (2012)
The Brain Prize (2017)
Scientific career
FieldsComputational neuroscience
Reinforcement learning
InstitutionsMax Planck Institute for Biological Cybernetics
University College London
Massachusetts Institute of Technology
Uber[1]
University of Toronto
Salk Institute
ThesisReinforcing connectionism : learning the statistical way (1991)
Doctoral advisorDavid Willshaw
Websitewww.kyb.tuebingen.mpg.de/person/95844/251691

Peter Samuel Dayan FRS is director at the Max Planck Institute for Biological Cybernetics in Tübingen, Germany. He is co-author of Theoretical Neuroscience,[4] an influential textbook on computational neuroscience. He is known for applying bayesian methods from machine learning and artificial intelligence to understand neural function and is particularly recognized for relating neurotransmitter levels to prediction errors and Bayesian uncertainties.[5] He has pioneered the field of reinforcement learning (RL) where he helped develop the Q-learning algorithm, and made contributions to unsupervised learning, including the wake-sleep algorithm for neural networks and the Helmholtz machine.[6][7][8]

Education

Dayan studied mathematics at the University of Cambridge and then continued for a PhD in artificial intelligence at the University of Edinburgh School of Informatics on statistical learning [9] supervised by David Willshaw and David Wallace, focusing on associative memory and reinforcement learning.[9]

Career and research

After his PhD, Dayan held postdoctoral research positions with Terry Sejnowski at the Salk Institute and Geoffrey Hinton at the University of Toronto. He then took up an assistant professor position at the Massachusetts Institute of Technology (MIT), and moved to the Gatsby Charitable Foundation computational neuroscience unit at University College London (UCL) in 1998, becoming professor and director in 2002.[10] In September 2018, the Max Planck Society announced his appointment as a director at the Max Planck Institute for Biological Cybernetics.[11]

Awards and honours

Dayan was elected a Fellow of the Royal Society (FRS) in 2018.[12] He was awarded the Rumelhart Prize in 2012 and The Brain Prize in 2017.[12]

References

  1. ^ Ghahramani, Zoubin (2017). "Welcoming Peter Dayan to Uber AI Labs". uber.com. Archived from the original on 15 March 2018.
  2. ^ Shead, Sam (2018). "Elon Musk Signed A 350-Year-Old Book With DeepMind's Demis Hassabis". forbes.com. Retrieved 9 February 2019.
  3. ^ Kumaran, Dharshan; Banino, Andrea; Blundell, Charles; Hassabis, Demis; Dayan, Peter (2016). "Computations Underlying Social Hierarchy Learning: Distinct Neural Mechanisms for Updating and Representing Self-Relevant Information". Neuron. 92 (5): 1135–1147. doi:10.1016/j.neuron.2016.10.052. ISSN 0896-6273. PMC 5158095. PMID 27930904.
  4. ^ Dayan, Peter; Abbott, Laurence (2014). Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems. Cambridge: MIT Press. ISBN 9780262541855. OCLC 952504127.
  5. ^ Schultz, W.; Dayan, P.; Montague, P. R. (1997). "A Neural Substrate of Prediction and Reward" (PDF). Science. 275 (5306): 1593–1599. doi:10.1126/science.275.5306.1593. ISSN 0036-8075. PMID 9054347. Closed access icon
  6. ^ Watkins, Christopher J. C. H.; Dayan, Peter (1992). "Q-learning". Machine Learning. 8 (3–4): 279–292. doi:10.1007/BF00992698. ISSN 0885-6125.
  7. ^ Dayan, Peter (1992). "The convergence of TD (λ) for general λ". Machine Learning. 8 (3/4): 341–362. doi:10.1023/A:1022632907294. ISSN 0885-6125.
  8. ^ Peter, Dayan; Hinton, Geoffrey E.; Neal, Radford M.; Zemel, Richard S. (1995). "The helmholtz machine". Neural Computation. 7 (5): 889–904. doi:10.1162/neco.1995.7.5.889. PMID 7584891. Closed access icon
  9. ^ a b Dayan, Peter Samuel (1991). Reinforcing connectionism: learning the statistical way (PhD thesis). hdl:1842/14754. EThOS uk.bl.ethos.649240. Free access icon
  10. ^ "Peter Dayan". gatsby.ucl.ac.uk. Archived from the original on 25 March 2019.
  11. ^ Anon (2018). "Peter Dayan and Li Zhaoping appointed to the Max Planck Institute for Biological Cybernetics". mpg.de. Archived from the original on 3 April 2019. Retrieved 2 October 2018.
  12. ^ a b Anon (2018). "Professor Peter Dayan FRS". royalsociety.org. London: Royal Society. Retrieved 22 May 2018. One or more of the preceding sentences incorporates text from the royalsociety.org website where:

    “All text published under the heading 'Biography' on Fellow profile pages is available under Creative Commons Attribution 4.0 International License.” --Royal Society Terms, conditions and policies at the Wayback Machine (archived 2016-11-11)

 This article incorporates text available under the CC BY 4.0 license.


Stub icon

This biography of an academic is a stub. You can help Wikipedia by expanding it.

Stub icon

This article about a neuroscientist is a stub. You can help Wikipedia by expanding it.

Retrieved from "https://en.wikipedia.org/enwiki/w/index.php?title=Peter_Dayan&oldid=930266456"