摘要
首先对BP网络的结构和算法进行了分析,针对BP网络收敛速度慢,容易陷入局部极小等问题,提出了一种改进的BP网络模型,并对该模型算法进行了改进,通过激活函数的选择,网络的初始化,学习率的调整和训练样本数据的处理等方法,可实现加快网络的收敛速度,并且较好的解决局部最优问题。
Based on analyzing structure and Algorithm of BP network, as for these problems of slow convergence and easily getting into the local minimum in the study algorithm of BP net, this paper designs one improved model of BP neural network. By choosing suitable activated function, taking its sensibility into accounts, and standing out researching the net＇s initializing matter etc, the faster convergence speed could be implemented and the problem of local optimization be solved better.
出处
《火力与指挥控制》
CSCD
北大核心
2009年第11期57-60,共4页
Fire Control & Command Control
关键词
BP网络模型
网络算法
神经元
BP network model, network algorithm, neural cell
