Research and Application on BP Neural Network Algorithm

Abstract

In the artificial neural network, BP neural network is a multilayer feedforward neural network which is used widely. BP neural network uses a classic BP algorithm, and it is in accordance with the error back-propagation algorithm for learning and training. This paper first analyzes the basic idea of BP algorithm, and using BP neural network model and the flow chart to illustrate; then, introduces the disadvantage of BP algorithm, has slow convergence and easy to fall into local minimum point and other defects, and describes the current improvements methods, such as adding momentum item, introduce variable step method and other optimization methods, which effectively improve the convergence of BP algorithm, to avoid falling into local minimum point; finally, describes in detail the application of BP neural network in face recognition. Effective research on BP neural network, which can be further development and application of BP networks play an important role.