A consideration on the learning algorithm of neural network-utilization of the hierarchical structure stochastic automata for the backpropagation method with momentum

摘要

Backpropagation (BP) method with momentum has often been applied to adapt artificial neural networks for various pattern classification problems. However, an important limitation of this method is that its learning performance depends heavily upon the selection of the values of momentum factor and step size. In this paper, it is shown that the hierarchical structure stochastic automata can be used for finding appropriate values of the parameters involved in the BP method with momentum.