I’ve always been interested in genetic algorithms – but how hard is it really to do something useful with that idea? I haven’t met the problem I couldn’t write at least a partial solution for with a couple hours of fiddling in Perl, so it will be interesting to see what I come up with. Stay tuned, folks!
May 27, 2008
1 Comment »
RSS feed for comments on this post. TrackBack URL
Leave a comment
You must be logged in to post a comment.
This article about Richard Feynman had a brief mention of simulated evolution running on a Thinking Machines massively-parallel supercomputer in the 1980s. I guess genetic algorithms are a pretty good “embarassingly parallel” problem. With 8 and 16-core systems going mainstream, and distributed systems becoming more accessible, maybe it’s time for a renaissance in genetic programming.
Comment by Matt Brubeck — May 30, 2008 @ 9:11 am