论文部分内容阅读
分析传统 BP算法存在的缺点 ,并针对这些缺点提出一种改进的 BP学习算法 .证明该算法在一定条件下是超线性收敛的 ,并且该算法能够克服传统 BP算法的某些弊端 ,算法的计算复杂度与简单 BP算法是同阶的 .实验结果说明这种改进的 BP算法是高效的、可行的 .
The disadvantages of the traditional BP algorithm are analyzed, and an improved BP learning algorithm is proposed according to these shortcomings. The algorithm proves that the algorithm converges linearly under certain conditions and overcomes the drawbacks of the traditional BP algorithm. The calculation of the algorithm The complexity is the same as the simple BP algorithm, and the experimental results show that the improved BP algorithm is efficient and feasible.