快速神经网络计算方法的探讨(Ⅰ)

Study on fast intelligent learning algorithm of neural network(Ⅰ)

探讨了一种快速神经网络的计算方法的建立思想 ,同时考虑到了全局收敛的问题 用遗传算法解决BP网络结构优化问题 ;采用模糊控制方法使遗传算法进程中Pc和Pm值自适应 ,其次 ,讨论实践过程中 。

One rapid computation algorithm is studied,simultantly,the global convergence is considered.Improve the construction of BP network by genetic algorithm;adjust the probabilities of crossover and mutation by the fuzzy control method.Then,disscuss the effective methods to improve the BP network in practice.