Feed-forward network training using optimal input gains

In this paper, an effective batch training algorithm is developed for feed-forward networks such as the multilayer perceptron. First, the effects of input transforms are reviewed and explained, using the concept of equivalent networks. Next, a non-singular diagonal transform matrix for the inputs is proposed. Use of this transform is equivalent to altering the input gains in the network. Newton´s method is used to solve for the input gains and an optimal learning factor. In several examples, it is shown that the final algorithm is a reasonable compromise between first order training methods and Levenburg-Marquardt.