Dynamic DBP learning algorithm for real time applications

Abstract

The paper extends an on-line neural network learning algorithm, DBP (derivative backpropagation), proposed by Jin et al to dynamic systems. The dynamic systems consist of linear systems and BackPropagation (BP) Neural Networks. The DBP algorithm learns the desired neural network outputs with respect to neural network inputs. This algorithm increases the position learning speed. Moreover in some neural adaptive control applications the partial derivatives of outputs to inputs are actually used. As argued in Narendra at al, dynamic neural network systems are very common in control applications, which gives a strong incentive to extending DBP to be a dynamic algorithm.