A stable learning algorithm for recurrent neural networks

Abstract

The authors used the Liapunov approach to derive a new set of sufficient conditions that explain the stability of feedforward networks. A simplification of these conditions results in a new recurrent backpropagation algorithm. This algorithm preserves the local updating characteristic of the original algorithm but is, at the same time, found to be quite effective even for problems which offered resistance to solution by L. B. Almeida's (1987) approach.<>