Skip to content

An experiment about an evolutionist machine learning

License

Notifications You must be signed in to change notification settings

splanard/evoluron

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

evoluron

An experimental evolutionist machine learning.

Introduction

Last year, I learned a bit about machine learning, especially the learning process of neural networks.

In the classic approach of machine learning, we measure a success score comparing the computed output and the expected one, and use it to improve the network. But this implies there is a "good" answer, and that we know it.

For some time now, I have wondered if we could apply the concept of species evolution to machine learning : define a neural network as a "specie", implement a mutation process, survival conditions and then simply wait for the survival of the most adapted version.

The aim of this project is to try and do that.

About

An experiment about an evolutionist machine learning

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages