1. I wanted to enhance it with the ability to have multiple brains (Networks)
2. I wanted to be Network Library agnostic, this repo creates a Synaptic-Adapter out-of-the-box but you can hook up any other NeuralNetwork library by creating a simple wrapper
3. I made some examples to have a playground starter for others.

Neuroevolution, or neuro-evolution, is a form of machine learning that uses evolutionary algorithms to train artificial neural networks. It is most commonly applied in artificial life, computer games, and evolutionary robotics. A main benefit is that neuroevolution can be applied more widely than supervised learning algorithms, which require a syllabus of correct input-output pairs. In contrast, neuroevolution requires only a measure of a network's performance at a task. For example, the outcome of a game (i.e. whether one player won or lost) can be easily measured without providing labeled examples of desired strategies.

Playing around with Neural Networks

import { Neuroevolution } from './node_modules/synaptic-neuroevolution';

Deep Neuroevolution: Genetic Algorithms are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning

Learn about the latest improvements

Want to correct a bug, contribute some code, or improve the codes? Excellent! Let me know! Please read CONTRIBUTING.md for details on our code of conduct.

This project is licensed under the MIT License - see the LICENSE.md file for details.