A survey on supervised learning by evolving multi-layer perceptrons

Abstract

This paper provides a guide to evolving-architecture neural networks for a beginner in multi-layer perceptrons. All the quoted methods aim at automatically fitting a neural network architecture to a particular classification task. Several kinds of evolving architectures are exposed. Some neural networks start small and become bigger and bigger during the learning, whereas others start over-dimensioned and undergo pruning. A last network category uses both methods alternately.