摘要
文章提出了基于粒子群优化的BP网络学习算法。在该算法中,用粒子群优化算法替代了传统BP算法中的梯度下降法,使得改进后的算法具有不易陷入局部极小、泛化性能好等特点。并将该算法应用在了高速公路动态称重系统的设计中,实验证明:这种算法能够明显减少迭代次数、提高收敛精度,其泛化性能也优于传统BP算法。
A BP neural networks learning algorithm based on Particle Swarm Optimizer(PSO) is proposed in this paper. Among this algorithm,PSO algorithm has substituted the gradient descent method in traditional BP algorithm,this new algorithm does not easily trapped local minima and has better generalization.The algorithm is applied to neural network's training in dynamic weighing system.The results show :this algorithm can reduce number of training and error obviously, it has better generalization than traditional BP algorithm.
出处
《计算机工程与应用》
CSCD
北大核心
2006年第16期41-43,66,共4页
Computer Engineering and Applications
关键词
BP网络
粒子群优化算法
泛化
BP neural networks,PSO algorithm,generalization
作者简介
潘昊(1964-),男,博士,副教授,主要研究方向:人工智能,软件工程,计算机网络。侯清兰(1980-),女,硕士,主要研究方向:智能算法。E-mail:houqlan24@126.com