Modified BP neural network model is used for oddeven discrimination of integer number

This paper introduced the BP neural network model and the BP algorithm in detail, and points out the BP neural network exists the defects of local optimal tendency of local optimal, slow convergence speed etc. Through the introduction of modified BP algorithm, we can solve the problems existing in the traditional BP algorithm successfully, simulation results for odd-even discrimination of integer number based on MATLAB BP algorithm show that modified BP model compared with BP model, has faster training speed and high study accuracy. Modified BP neural network models is used in practice, as long as it is complementary with effective measures, and we can get satisfactory result completely.