From: Mikko Särelä (msarela@cc.hut.fi)
Date: Sat Mar 19 2005 - 00:04:11 MST
On Fri, 18 Mar 2005, Ben Goertzel wrote:
> As a teaser, though, I'll note that I did a fair amount of work with
> MAXENT a while back. It's powerful but yet the maximum-entropy
> assumption about priors isn't really good enough. Yet the
> Solomonoff-Levin prior is intractable.... Is there a "middle ground"
> (not quite the right expression, I know) that works for AGI yet is
> tractable? IMO this "middle ground" is going to involve a heck of a lot
> of stuff that has nothing directly to do with Bayes theorem but a lot to
> do with cognitive science..
Some interesting things possibly on the middle ground are (self organising
maps and independent component analysis. They are computationally feasible
and show some promise.
-- Mikko Särelä ... In areas which do not fall within its exclusive competence, the Union shall act only if ... objectives of the proposed action ... can rather, by reason of the scale or effects of the proposed action, be better achieved at Union level.
This archive was generated by hypermail 2.1.5 : Tue Feb 21 2006 - 04:22:55 MST