Neural network BP training algorithm based on gradient descend technique may lead to entrapment in local optimum so that the network inaccurately classifies input patterns.

基于梯度下降的神经网络训练算法易于陷入局部最小，从而使网络不能对输入模式进行准确分类。

youdao

The approaches based on ANN or gradient hill climb algorithm have limitations such as the function form and local optimum.

采用人工神经网或梯度爬山算法均存在对优化函数形式有限制及陷入局部最优等局限性。

youdao

This paper discussed two basic problems of conventional BP algorithm. A improved BP algorithm based on step optimum and conjugate gradient was put forword in this paper.

本文针对传统BP算法存在的两个常见问题进行了讨论，提出了基于步长优化和共轭梯度法的改进BP算法。

youdao