计算技术与自动化Issue(4)：86-89,4.
BP 神经网络的改进
Improved BP Neural Network
胡丽 1陈斌 2赖启明 1何振平3
作者信息
- 1. 海军工程大学 电子工程学院，湖北 武汉 430033
- 2. 海军 705 工厂，广东 湛江 524000
- 3. 海军 705 工厂，广东 湛江 524000
- 折叠
摘要
Abstract
This paper mainly aimed at avoiding local minimum of BP neural network and improving the convergence rate. Through the sample analysis of BP neural network,the correlation coefficient between the training obj ective function and the input vector was obtained,and the initial weights of the BP neural network were obtained by the correlation coefficient.And the experiments have achieved the expected goal.关键词
BP神经网络/收敛速度/初始权重/局部最小Key words
BP neural network/the initial weight/local minima分类
信息技术与安全科学引用本文复制引用
胡丽,陈斌,赖启明,何振平..BP 神经网络的改进[J].计算技术与自动化,2015,(4):86-89,4.
