Generalization of the cross-entropy error function to improve the error backpropagation algorithm

This paper generalizes the cross-entropy error function to improve the EBP (error back propagation) algorithm of multilayer perceptrons. The generalized error function reduces the probability that output nodes are near the wrong extreme value as well as the correct extreme value of sigmoid function. As a result, we can accelerate the learning speed of the EBP algorithm with improved generalization performance. The effectiveness of the proposed method is demonstrated in a handwritten digit recognition task