A demonstration on different ways to train neural networks. The BodyHammer project uses a packpropagation method to train a neural network to recognize a small set of test symbols and demonstrates a practical use for neural networks. The Tetsuo project uses a genetic algorithm to define the fitness of each 'creature' and, through natural selection, optimizes the neural network.
This repository has been archived by the owner on Jul 10, 2020. It is now read-only.