ct-neat-python 1.1.0

A CT (Continuous Time) NEAT (NeuroEvolution of Augmenting Topologies) implementation

About

NEAT (NeuroEvolution of Augmenting Topologies) is a method developed by Kenneth O. Stanley for evolving arbitrary neural networks. Later NEAT was extended to evolve CT (Continuous Time) networks in different frameworks. This project is a Python implementation of CT-NEAT (and has both pure NEAT and CT-NEAT implementations) with few dependencies beyond the standard library (like scikit-learn). It was forked from the excellent project started by @MattKallada and continued by @CodeReclaimers (neat-python) after their project was archived.

For further information regarding general concepts and theory, please see the Selected Publications on Stanley's page at the University of Central Florida (now somewhat dated), or the publications page of his current website. (rtNEAT would be relevant for the CT element.)

ct-neat-python is licensed under the 3-clause BSD license. It is currently supported on Python 3.8 through 3.13, and pypy3.

Getting Started

If you want to try ct-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.

The package can be install from PyPI using:

pip install ct-neat-python

The documentation is available on Read The Docs.

If you want to contribute to the directory and run the code in a developer setting, run the following from the root of the project:

pip install -e .

This will install the package in a dynamically linked mode such that all of your changes will be immediately reflected.

Citing

Here are APA and Bibtex entries you can use to cite this project in a publication. The listed authors are the originators and/or maintainers of all iterations of the project up to this point. If you have contributed and would like your name added to the citation, please submit an issue or email [e-mail].

APA

Horef, S., McIntyre, A., Kallada, M., Miguel, C. G., Feher de Silva, C., & Netto, M. L. ct-neat-python [Computer software]

Bibtex

@software{Horef_ct-neat-python,
author = {Horef Sergiy, McIntyre, Alan and Kallada, Matt and Miguel, Cesar G. and Feher de Silva, Carolina and Netto, Marcio Lobo},
title = {{ct-neat-python}}
}