Marcus Hutter

We have the privilege of having Marcus Hutter, Professor in the Research School of Computer Science (RSCS) at the Australian National University (ANU) in Canberra and senior researcher in the National Information and Communication Technology of Australia (NICTA)!

 

Universal Artificial Intelligence. Sequential decision theory formally solves the  problem of rational agents in uncertain worlds if the true environmental probability distribution is known. Solomonoff’s theory of universal induction formally solves the problem of sequence prediction for unknown distribution. With a formal solution I mean a rigorous mathematically definition, uniquely specifying the solution. I unified both theories and gave strong arguments that the resulting universal AIXI model behaves optimally in any computable environment. I also made some progress towards a computable AI theory. I constructed an algorithm AIXItl, which is superior to any other time t and space l bounded agent. The computation time of AIXItl is of the order t·2^l. The constant 2^l is still too large to allow a direct implementation. My main focus is on theoretical studies related to the AIXI model and on further reducing the time-complexity of AIXItl down to a point where it runs on todays computers with reasonable computation time. This apporach may be characterized as a mathematical top-down approach to AI.

Ray Solomonoff (read by Marcus Hutter) – Algorithmic Probability, Heuristic Programming and AGI

Also see:
http://2012.singularitysummit.com.au/2012/08/universal-artificial-intelligence/
http://2012.singularitysummit.com.au/2012/08/panel-intelligence-substrates-computation-and-the-future/
http://2012.singularitysummit.com.au/2012/01/marcus-hutter-to-speak-at-the-singularity-summit-au-2012/