Methods of training and constructing multilayer perceptrons with arbitrary pattern sets

This paper presents two compensation methods for multilayer perceptrons (MLPs) which are very difficult to train by traditional Back Propagation (BP) methods. For MLPs trapped in local minima, compensating methods can correct the wrong outputs one by one using constructing techniques until all outputs are right, so that the MLPs can skip from the local minima to the global minima. A hidden neuron is added as compensation for a binary input three-layer perceptron trapped in a local minimum; and one or two hidden neurons are added as compensation for a real input three-layer perception. For a perceptron of more than three layers, the second hidden layer from behind will be temporarily treated as the input layer during compensation, hence the above methods can also be used. Examples are given.