摘要： 从前馈神经网络原理分析出发，提出一种速率适应因子方法用于对多层前馈神经网络中BP算法的改进，并将改进的算法用于XOR问题的学习及多重XOR分类器问题的学习。仿真结果表明，改进后BP的算法可显著加速网络的学习速度，并且学习过程具有良好的收敛性及较强的鲁棒性。

关键词: 前馈神经网络, BP算法, XOR

Abstract: According to the mechanism of Feedforward Neural Network(FNN), this paper describes a method with variable learning rate factors for the improvement of BP algorithm. The improved algorithm is applied to the learning of the XOR question and some classification process. The simulations show the improved algorithm has good effects on speeding up learning process and bettering its learning convergence and robust performance.

中图分类号: 

• TP183