Study On Improved Algorithm And Application Of BP Neural Network

Artificial neural network is a nonlinear system which simulates cerebrum information processing algorithm. It has powerful distributed information storage, parallel processing and adaptive learning ability. Because of simple structure, high accuracy, easy to program and operate, good nonlinear mapping capability, back propagation network is becoming one of the widely used neural networks at present.BP algorithm uses the steepest descent algorithm, thus there are two main shortcomings of slow convergence rate and easy to fall into local minimum. According to this, a lot of scholar researched on the basis of the standard BP algorithm and presented many improved back propagation algorithms from the factor of the learning rate, error function, activation function, optimization algorithm, the network structure and other aspects.Firstly, we expound back-propagation networks systematically in this paper. For the platform phenomenon of standard back-propagation algorithm, an adaptive magnified error signal is constructed. The derivative of the activation function is modified to make the weight adjustment avoid falling into the saturation areas. Then the theorem for the convergence of the proposed algorithm is presented and proved. Secondly, considering the learning rate factor of influencing BP networks performance, this paper presents an adaptive learning rate adjustment of improved BP algorithm.In view of the BP algorithm's flaw, this paper makes the improvement from two different perspectives to the standard BP algorithm. In order to verify the effect of the new algorithm, we use the new algorithms to solve function approximation and the identification of odd or even problems. We also contrast the new algorithm with standard back propagation algorithm. The simulation results show that the improved algorithms have quick convergence rate, strong optimization ability and good value of application and reference.