GA and EA algoritm examples

Started by
3 comments, last by willh 12 years ago
[color=#000000][font=verdana, arial, helvetica, sans-serif]

I need some examples for Genetic and Evolutionary algorithms in C++.[/font]
[color=#000000][font=verdana, arial, helvetica, sans-serif]

For solving different problems, not only the Traveling Salesman Problem.[/font]
[color=#000000][font=verdana, arial, helvetica, sans-serif]

I couldn't find any myself, not in c++.[/font]
[color=#000000][font=verdana, arial, helvetica, sans-serif]

I need plain code.[/font]

Advertisement
Really? Koza, google him, has a bunch of patents for things discovered by ga. There's that evolving car demo people like, and lots of stuff on YouTube.
Methinks you might not have looked hard enough.

Dave Mark - President and Lead Designer of Intrinsic Algorithm LLC
Professional consultant on game AI, mathematical modeling, simulation modeling
Co-founder and 10 year advisor of the GDC AI Summit
Author of the book, Behavioral Mathematics for Game AI
Blogs I write:
IA News - What's happening at IA | IA on AI - AI news and notes | Post-Play'em - Observations on AI of games I play

"Reducing the world to mathematical equations!"

Me thinks you probably wrong. I find a lot of tutorials and other things that start with the basics. And I found some free lectures from Stanford University on Machine Learning, but I can't find plain code.
I doubt you will find much code because the GA part is trivial. The work is in parsing, executing, and scoring each permutation and this is very problem specific.

There is an interesting video on YouTube of a GA used to find an better wind mill blade design. The gentleman used a fluid dynamics simulator, which he did not write himself, to test each blade design.

There is another example on YouTube of finding an optimal location for a radio antenna on a HUM V. The GA code would have just been a set of coordinates (3 numbers I'm guessing), but to test each placement there would have been some pretty sophisticated simulation package that was employed.

NEAT uses GA as a leaning algorithm for neural networks. Some commercial data mining packages include GAs to refine decision trees. There is a commercial function "solver" (video on YouTube) that uses EP exclusively to find an equation to fit data.

Keep looking. There is a lot of stuff out there.

This topic is closed to new replies.

Advertisement