摘要
本文给出前馈神经网络的一种连续型学习算法，对传统的ＢＰ算法作了改进。分析了该算法的收敛性。通过实例与传统ＢＰ算法进行比较，该算法可以明显提高网络的收敛速度，说明它是一种实用的学习算法。
This paper proposes a continuous learning algorithm for feedforward neural networks, an improvement of the traditional BP algorithm. Meanwhile,its convergence is analyzed. By virtue of examples, compared with the traditional BP algorithm,this algorithm can remarkably increase the converging speed of networks.This indicates the algorithm is a practical one.
出处
《系统工程与电子技术》
EI
CSCD
1996年第2期53-57,共5页
Systems Engineering and Electronics
关键词
学习算法
前馈神经网络
神经网络
Feedforward neural networks,Continuation,Learning algorithm.
