SIGNAL FLOW-GRAPHS AND NEURAL NETWORKS

The application of signal flow graphs to the learning process of neura l networks is presented. By introducing the so-called adjoint graph, n ew insight into the mechanism of learning phenomena of the weights in neural networks has been obtained. The derived updating formulas are v alid for both feedforward and recurrent neural networks and are especi ally useful from the hardware implementation point of view of the self -learning networks. The presented numerical experiments confirmed the usefulness of the presented approach.