Disadvantages of the back propagation algorithm are discussed, and the improved methods based on dynamic learning constants and different activation functions are presented.
讨论了误差逆传播算法存在的缺陷，并针对其缺陷提出了动态调整学习因子与合理选取激发函数相结合的改进方案。
Disadvantages of the back propagation algorithm are discussed, and the improved methods based on dynamic learning constants and different activation functions are presented.
讨论了误差逆传播算法存在的缺陷，并针对其缺陷提出了动态调整学习因子与合理选取激发函数相结合的改进方案。
应用推荐