Study on Elman Neural Networks Algorithms Based on Factor Analysis

When we manipulate high dimensional data with Elman neural network, many characteristic variables provide enough information, but too many network inputs go against designing of the hidden-layer of the network and take up plenty of storage space as well as computing time, and in the process interfere the convergence of the training network, even influence the accuracy of recognition finally. Factor Analysis (FA) concentrates the information that is carried by numerous original indexes which form the index system, and then stores it to the factor, and can according to the precision that the actual problem needs, through controlling the number of the factors, to adjust the amount of the information. In this paper we make full use of the advantages of FA and the properties of Elman neural network structures to establish FA-Elman algorithm. The new algorithm reduces dimensions by FA, and carry on network training and simulation with low dimensional data that we get, which obviously simplifies the network structure, and in the process, improves the training speed and generalization capacity of the Elman neural network.