摘要
快速神经网络训练算法的研究是人们所关注的问题之一。经过分析与研究 ,遗传算法是一种全局并行随机搜索优化算法 ,具有很强的全局搜索能力 ,而 BP算法的局部搜索能力较强。文章将两者结合起来 ,形成一种混合遗传算法 ,并就混合遗传算法的原理及其在实现时所涉及到的许多策略问题进行了分析比较 ,仿真结果表明它具有收敛速度快和不会陷入局部极小的特点。
Researchers' attention has been drawn to the research on fast neural network training algorithm for a long time. The genetic algorithm(GA) is a kind of optimization algorithm with which global, parallel and random searching can be achieved, and its global searching performance is very good, while the BP algorithm does quite well in local searching. By adding BP algorithm into GA, a new algorithm called hybrid genetic algorithm(HGA) is formed. In this paper, the principle and strategies of the new algorithm are analyzed and summarized, and the new algorithm is compared with BP algorithm.Simulation results show that the new algorithm has the advantage of fast convergence and it will not converge at the local nadir.
出处
《合肥工业大学学报（自然科学版）》
CAS
CSCD
2001年第5期901-906,共6页
Journal of Hefei University of Technology：Natural Science
基金
国家自然科学基金资助项目 ( 5 0 0 770 0 5 )
关键词
神经网络
训练算
遗传算法
混合遗传算法
BP算法
neural network
training algorithm
genetic algorithm
hybrid genetic algorithm
