We closed this forum 18 June 2010. It has served us well since 2005 as the ALPHA forum did before it from 2002 to 2005. New discussions are ongoing at the new URL http://forum.processing.org. You'll need to sign up and get a new user account. We're sorry about that inconvenience, but we think it's better in the long run. The content on this forum will remain online.
IndexProcessing DevelopmentLibraries,  Tool Development › Genetic Algorithm, new and improved!
Page Index Toggle Pages: 1
Genetic Algorithm, new and improved! (Read 1076 times)
Genetic Algorithm, new and improved!
May 11th, 2009, 2:47pm
 
Cedric contacted me recently about using my GA library. I remembered someone contacting me about it having a bug in it a while back so I thought I would fix it properly this time.

Which turned into re-writing most of it. Here's some of the billion things I changed:

It now uses ArrayLists instead of Vectors

Descriptive error handling has been added, given that genetic algorithms are a black box to most people.

The binary splicing operations can now be controlled by the user, meaning you treat integer arrays as binary strings and splice them with more control. I've also detailed how to splice binary ints outside of the GA in the reference.

Names of methods have been changed to protect the innocent.

Binary masking tables are now statically available (god knows why they weren't before).

You no longer have to extend GeneticAlgorithm to use Chromosomes.
And properties are no longer accessed via methods. For some applications this is good practise, but in AI where speed is of great importance, it's lunacy.

There's probably other things I've changed too.

Any feature requests and you know where to find me. I'll be trying to put together some simple graphical examples of things to play with instead of that confusing math example in the next few weeks. That and getting the reference in alphabetical order.

http://www.robotacid.com/PBeta/AILibrary/GA/index.html

Enjoy.
Page Index Toggle Pages: 1