Los puntos clave no están disponibles para este artículo en este momento.
A new learning algorithm for neural networks of spin glass type is proposed. It is found to relax exponentially towards the perceptron of optimal stability using the concept of adaptive learning. The patterns can be presented either sequentially or in parallel. A prove of convergence is given and the method's performance is studied numerically.
Anlauf et al. (Fri,) studied this question.