计算机与现代化Issue(6)：91-94,4.DOI:10.3969/j.issn.1006-2475.2011.06.026
基于遗传模拟退火算法优化的BP神经网络
BP Neural Network Optimization Algorithm Based on Genetic-stimulated Annealing
吕琼帅 1王世卿1
作者信息
- 1. 郑州大学信息工程学院,河南,郑州,450002
- 折叠
摘要
Abstract
After studying the disadvantage of BP neural network which has low convergent speed and trap into local minima easily,an idea of designing a new hybrid neural network model which adopts the method of numerical optimization is presented. By using Genetic-Stimulated Annealing algorithm (GSA), expands the updated space of weight. On the basis, it makes the acquired better value as the weight of BP neural network, and the optimized BP network is not easy to trap into the local minima and has good generalization characteristic. Making the comparation GSA network with standard BP network, simulation analysis demonstrates that this network model can attain higher categories of precision.关键词
数值优化/遗传模拟退火算法/BP神经网络/权值/泛化性Key words
numerical optimization/ genetic-stimulated annealing algorithm/ BP neural network/ weight/ generalization分类
信息技术与安全科学引用本文复制引用
吕琼帅,王世卿..基于遗传模拟退火算法优化的BP神经网络[J].计算机与现代化,2011,(6):91-94,4.
