FORK STATUS
This is a fork from CodeReclaimers. I have been fascinated by the project and I started applying some changes and improvement myself but also from the community. I cannot guarantee to push lot of new features or fix any issue, but I will do my best to actively check any Pull Request coming in!
About
NEAT (NeuroEvolution of Augmenting Topologies) is a method developed by Kenneth O. Stanley for evolving arbitrary neural networks. This project is a pure-Python implementation of NEAT with no dependencies beyond the standard library. It was forked from the excellent project by @MattKallada, and is in the process of being updated to provide more features and a (hopefully) simpler and documented API.
For further information regarding general concepts and theory, please see Selected Publications on Stanley's website.
neat-python
is licensed under the 3-clause BSD license.
Getting Started
If you want to try neat-python, please check out the repository, start playing with the examples (examples/xor
is
a good place to start) and then try creating your own experiment. Always check the
differences between this fork and the main repo
to decide which one is the more appropriate for your needs.
If you want to use this fork, the PyPi package name is currently neat-python-gicminos
.
The documentation, is available on Read The Docs.
Citing
Here is a Bibtex entry you can use to cite this project in a publication. The listed authors are the maintainers of all iterations of the project up to this point.
@misc{neat-python,
Title = {neat-python},
Author = {Alan McIntyre and Matt Kallada and Cesar G. Miguel and Carolina Feher da Silva},
howpublished = {\url{https://github.com/CodeReclaimers/neat-python}}
}