BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:What Can be Automated: A Viewpoint from Learning and Evolution
DTSTART:20170501T161500
DTEND:20170501T171500
DTSTAMP:20260415T032246Z
UID:150144a6e8c2d67693961fd3b5b40d3b4382fddcbb055b88372a989d
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Leslie Valiant\, Harvard University   \nBio: Leslie Va
 liant was educated at King's College\, Cambridge\; Imperial College\, Lond
 on\; and at Warwick University where he received his Ph.D. in computer sci
 ence in 1974. He is currently T. Jefferson Coolidge Professor of Computer 
 Science and Applied Mathematics in the School of Engineering and Applied S
 ciences at Harvard University\, where he has taught since 1982. Before com
 ing to Harvard he had taught at Carnegie Mellon University\, Leeds Univers
 ity\, and the University of Edinburgh.\n \nHis work has ranged over sever
 al areas of theoretical computer science\, particularly complexity theory\
 , learning\, and parallel computation. He also has interests in computatio
 nal neuroscience\, evolution and artificial intelligence and is the author
  of two books\, Circuits of the Mind\, and Probably Approximately Correct.
 \n \nHe received the Nevanlinna Prize at the International Congress of Ma
 thematicians in 1986\, the Knuth Award in 1997\, the European Association 
 for Theoretical Computer Science EATCS Award in 2008\, and the 2010 A. M. 
 Turing Award. He is a Fellow of the Royal Society (London) and a member of
  the National Academy of Sciences (USA).\nPlease see his website for more 
 information.\nIC Distinguished Lecture\n\nWith machine learning technology
  we are now able to automate many tasks that humans learn to perform throu
 gh experience rather than through step-by-step instruction. Without such a
  learning capability we are limited to automating tasks for which a step-b
 y-step sequence of instructions is known. In this talk we shall ask whethe
 r it is possible to circumscribe the set of tasks that we can expect to ef
 fectively automate. The discussion will start from the hypothesis that all
  the information that resides in living organisms was initially acquired e
 ither through learning by an individual or through evolution. Then any uni
 fied theory of evolution and learning should be able to characterize the c
 apabilities that humans and other living organisms can potentially acquire
  and perform. Characterizing these capabilities would tell us about the na
 ture of humans\, but would also inform us about feasible targets for autom
 ation. We shall discuss where we are with such a unified theory.\n \n\n 
 \n\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR