AForge.NET

  :: AForge.NET Framework :: Articles :: Forums ::

Genetic programming to evolve classifiers.

The forum is to discuss topics from different artificial intelligence areas, like neural networks, genetic algorithms, machine learning, etc.

Genetic programming to evolve classifiers.

Postby puneeth » Sat Oct 15, 2011 4:51 am

Hi Andrew,

Im trying to build a GP which evolves classifiers. (binary classification).
Is it possible in AForge.NET ?

I have set of inputs which belongs to either of two class - class 1 / class 2.
want to evolve the classifiers in GP.

thanks in advance
puneeth
 
Posts: 1
Joined: Sat Oct 15, 2011 4:46 am

Re: Genetic programming to evolve classifiers.

Postby andrew.kirillov » Mon Oct 17, 2011 4:40 am

Hello,

The AForge.NET framework can be used to solve some GP problems. All you need is to define proper fitness function and create proper chromosome with crossover/mutation operators. However, there is already GP chromosome class implemented, so potentially it may work for you.

See some sample applications provided with the framework to see how to use Genetic Programming for tasks like approximation.
With best regards,
Andrew


Interested in supporting AForge.NET Framework?
User avatar
andrew.kirillov
Site Admin, AForge.NET Developer
 
Posts: 3446
Joined: Fri Jan 23, 2009 9:12 am
Location: UK




Return to Artificial Intelligence