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

Matt Gingell (mjg223@nyu.edu)
Wed, 8 Sep 1999 01:59:04 -0400

>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

I believe this approach is provable optimal in the absence of any knowledge about the shape of the search space, but I'm having trouble tracking down the reference.

A while back, I wrote an artificial life system which simulates a population of organisms driven by neural networks. Unfortunately, I have to report that a herd of parallel searches most certainly can get stuck! (In my case, I was dealing with populations of around one or two thousand nodes.)

-matt