Re: Mike Perry's work on self-improving AI

From: Rik van Riel (riel@humbolt.geo.uu.nl)
Date: Tue Sep 07 1999 - 08:48:18 MDT


On Tue, 7 Sep 1999, Matt Gingell wrote:

> I don’t think there can be any general solution to the problem of
> local optima. There are lots of different useful techniques, but any
> hill-climbing algorithm can potentially get stuck. It’s a question of
> the topology of the search space, which can be arbitrarily complex

If you use a 'population' of searches, combined with multiplication
(split the ones at a good point in space and remove the bottom
feeders) and random bitflipping (flip a random bit in 10% of the
searchers) you might be able to get around the problem.

Rik

--
The Internet is not a network of computers. It is a network
of people. That is its real strength.
--
work at:	http://www.reseau.nl/
home at:	http://www.nl.linux.org/~riel/


This archive was generated by hypermail 2.1.5 : Fri Nov 01 2002 - 15:05:03 MST