BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Information and Intelligence - Alex Selby
DTSTART:20050608T140000Z
DTEND:20050608T150000Z
UID:TALK4325@talks.cam.ac.uk
CONTACT:Phil Cowans
DESCRIPTION:If we were to try to construct an intelligent machine\, what\,
  in very broad\nterms\, would we be aiming to do? It can be argued that th
 e answer is\n(roughly speaking) to compress data as efficiently as possibl
 e. This leads\nto the idea of "Kolmogorov Complexity" (and related measure
 s)\, which also\narises as the universal prior for probabilistic inference
 .\n\nFor fun\, consider the following question: Suppose someone said that 
 in one\nhour's time you could have 1 second of computing time on a compute
 r which\nexecuted 10^(10^100) instructions per second\, had a similarly la
 rge amount\nof memory\, and started with a copy of the internet and all th
 e libraries\nof the world (and possibly some other real world data) in its
  memory. At\nthe end of the 1 second you get to keep a reasonable amount o
 f output (say\n10^12 bytes). What program would you write? What would your
  answer be if\nthe computer started off with a blank memory?\n\nSome backg
 round reading for those interested:\n\nhttp://www.idsia.ch/~juergen/locone
 t/nngen.html\nhttp://www.geocities.com/jim_bowery/cprize.html\nhttp://peop
 le.cs.uchicago.edu/~fortnow/papers/soph.pdf\nhttp://citeseer.ist.psu.edu/g
 acs93lecture.html\nhttp://homepages.cwi.nl/~paulv/papers/algorithmicstatis
 tics.pdf\n\n
LOCATION:Ryle Seminar Room\, Cavendish Laboratory
END:VEVENT
END:VCALENDAR