A robust learning algorithm of layered neural networks, - H{sub}∞ filtering approach

摘要

Back propagation (BP) method is widely used as a learning algorithm of layered neural networks. However, the learning rate is too late, and it is affected by the initial values of weight coefficients and thresholds. In this paper, a robust learning algorithm is derived based on H{sub}∞ filter (HF), comparing with back propagation and Kalman filter (EP) learning algorithms. The robustness of HF learning algorithm is verified by computer simulations.