Structural learning of MTM-MLP based on individual evolutionary algorithm

The purpose of structural learning is to determine the structure as well as the weights of a neural network. For large-scale networks, structural learning is a very difficult problem. To solve this problem efficiently, we have proposed the individual evolutionary algorithm (IEA), which can produce NN-MLP (nearest neighbor based multilayer perceptron) with the least or almost least number of hidden neurons. We apply IEA to the learning of MTM-MLP (multi-template matching based MLP). The goal is to obtain networks with the least number of hidden neurons as well as the least number of synapses. The performance of the IEA is shown by experimental results