NashCoding Yet Another Artificial Intelligence Blog

29Oct/103

Tutorial – Evolving Neural Networks with SharpNEAT 2 (Part 3)

In parts 1 and 2 of this tutorial series, we evolved neural networks using the standard NEAT algorithm. In part 3, we're going to use the HyperNEAT algorithm.

24Jul/109

Tutorial – Evolving Neural Networks with SharpNEAT 2 (Part 2)

In part 1 of the tutorial, we setup a basic experiment to evolve a neural network to play Tic-Tac-Toe against a couple of hand-coded opponents. In part 2, we're going to create a competitive coevolution experiment where the networks evolve by playing against themselves.

17Jul/104

Tutorial – Evolving Neural Networks with SharpNEAT 2 (Part 1)

The Neuro-Evolution via Augmenting Topologies (NEAT) algorithm enables users to evolve neural networks without having to worry about esoteric details like hidden layers. Instead, NEAT is clever enough to incorporate all of that into the evolution process itself. You only have to worry about the inputs, outputs, and fitness evaluation.

This is a tutorial on how to use SharpNEAT 2, the second version of a popular C# implementation of the NEAT algorithm written by Colin Green. The source code for this tutorial is available here.