#machine-learning #genetic-algorithm #neat

tyrosine-common

Implementation of NEAT with CUDA support

1 unstable release

0.0.1 Dec 23, 2023

#16 in #neat


Used in tyrosine

GPL-2.0 OR GPL-3.0

22KB
447 lines

Tyrosine

Tyrosine Mascot Mascot by @Nauxe

Overview

NEAT machine learning library for Rust and Python. Tyrosine is implemented using Rust and CUDA (for hardware acceleration). For Python bindings, PyO3 is used.

NeuroEvolution of Augmenting Topologies (NEAT) is a genetic algorithm which evolves a population of neural networks. NEAT aims to find an optimal set of weights in addition to an optimal neural network structure.

Trivia

Tyrosine is an amino acid. The word comes from the Greek "tyros", which means cheese.

License

This work is dual-licensed under GPL Version 2 and GPL Version 3. You may choose between these licenses on a case-by-case basis.

Dependencies

~605KB
~11K SLoC