A new scheme for training feed-forward neural networks

摘要

In this paper we present a new algorithm, which is orders of magnitude faster than the delta rule, for training feed-forward neural networks. It provides a substantial improvement over the method of Scalero and Tepedelenlioglu (IEEE Trans. Signal Process. 40(1) (1992)) in both training time and numerical stability. The method combines the modified back-propagation algorithm described by Scalero and Tepedelenlioglu along with a faster training scheme and has better numerical stability. The algorithm is tested against other methods, and results are presented.