Crate neuralneat

neuralneat is an implementation of the NeuroEvolution of Augmenting Topologies (NEAT) described in the June 2002 paper titled “Evolving Neural Networks through Augmenting Topologies” by Kenneth O. Stanley and Risto Miikkulainen.

Much of this implementation was also guided by the NEAT 1.2.1 source code.

Basic usage:

use neuralneat::{Genome, Pool, Trainer};
use neuralneat::evaluation::TrainingData;

// To do something useful, you need to decide what your training data is!
fn load_training_data() -> Vec<TrainingData> {
    return vec![];
}

fn main() {
    let input_nodes = 5;
    let output_nodes = 1;
    // Create an initial pool of Genomes
    let mut gene_pool = Pool::with_defaults(input_nodes, output_nodes);
     
    // Load the data that will be used to train and evolve the Genomes
    let training_data: Vec<TrainingData> = load_training_data();
     
    // A Trainer can manage the process of training a population of Genomes
    // over successive generations.
    let mut trainer = Trainer::new(training_data);
     
    trainer.train(
        &mut gene_pool,
        // Train for 100 generations
        100,
    );

    // The winner!
    let best_genome = gene_pool.get_best_genome();
}

Modules

defaults

The defaults module contains the default values of all of the constants used by the Pool to create, mutate, and mate Genomes.

evaluation

The evaluation module contains functions and types related to the process of evaluating and activating the neural network of a Genome, such as basic activation functions that can be used with hidden and output layers of a Genome.

Structs

Genome

A Genome contains a network of Network of Neurons and Genes that when given the same number of inputs the containing Pool was given, will produce a Vec with the same number of outputs that the Pool was given.

GenomeStats

Basic statistics about a Genome’s fitness.

Pool

A “Gene” Pool that contains and manages a population of Genomes separated into one or more Species.

PoolStats

Basic statistics about a Pool and the Species and Genomes contained within it.

Species

A Species contains a number of Genomes that share common structure.

SpeciesStats

Basic statistics about a Species and the Genomes contained within it.

Trainer

A Trainer will manage the training cycle for a population of Genomes.