【摘要】 目的　通过MATLAB实现BP神经网络的改进算法.方法　采用了动量法和学习率自适应调整的策略.结果　运用MATLAB对BP神经网络进行初始化和训练.结论　实践证明,改进了的BP神经网络算法,提高了学习速度,增加了算法的可行性.利用MATLAB软件提供的工具箱编制BP网络解决非线性问题是一种便捷、有效、省事的途径.更多还原

【Abstract】 Aims\ To realize an improved arithmetic of BP neural networks based on the MATLAB. Methods\ Method of momentum and strategy is adopted for adjusting learning efficiency. Results\ Applying MATLAB to initialize and train BP neural networks. Conclusion\ Practice had proved: an improved arithmetic of BP neural networks improves the speed of learning and builds up the feasibility of arithmetic. It is a facile, effective and trouble saving way to make use of the toolboxes supplied by MATLAB.更多还原