AN IMPROVED TIME-SERIES PREDICTION BY APPLYING THE LAYER-BY-LAYER LEARNING-METHOD TO FIR NEURAL NETWORKS

The FIR neural network model was recently proposed for time series pre diction and gave good results. However the learning algorithm used for the FIR network is a kind of gradient descent method and hence inheri ts all the well-known problems of the method. Recently a new learning algorithm called the optimization layer by layer was proposed for the regular multilayer perceptron network, and showed a great improvement in the learning time as well as the performance of the network. In thi s paper we develop a new learning algorithm for the FIR neural network model by applying the idea of the optimization layer by layer to the model. The results of the experiment, using two popular time series pr ediction problems, show that the new algorithm is far better in learni ng rime and more accurate in prediction performance than the original learning algorithm. (C) 1997 Elsevier Science Ltd. All rights reserved .