开发环境:Matlab

简要说明:动量-自适应学习调整算法。在实际应用中，原始的BP算法很难胜任，因此出现了很多的改进算法。BP算法的改进主要有两种途径，一种是采用启发式学习方法，另一种则是采用更有效的优化算法。本例采用动量BP算法，来实现对网络的训练过程，动量法降低了网络对于误差曲面局部细节的敏感性，有效地抑制网络陷于局部极小。-development environment : Matlab Brief Descr iption : Momentum-adaptive learning algorithm adjustments. In practical application, the original BP algorithm competence, resulting in a lot of improved algorithm. BP algorithm improvements There are two main ways of using a heuristic approach to learning Another is the use of a more effective method of optimization. Momentum cases using the BP algorithm to achieve the network training process, Momentum for reducing error of the network for local surface details of the sensitivity, to effectively curb the network into local minima.