摘要
遗传算法是一种新的、基于自然选择和基因遗传学原理的随机搜索算法．针对神经网络中BP算法学习效率低且收敛速度慢以及容易陷入局部最优等不足,文章提出利用遗传算法对 BP神经网络中的神经元间的连接权值进行优化的方法．试验结果表明,用遗传算法优化BP神经网络的连接权值后收敛速度快,并有效的解决了BP算法容易陷入局部最优的问题．
The genetic algorithm （GA） is a new random search algorithm based on natural selection and the principle of gene genetics. As the BP algorithm there are some shortages, so such low efficiency of study, slow speed of constringency, and easy to be trapped into local optimization, etc. , the paper puts forward the method that utilizes the genetic algorithm optimizing the weights among the neuron in BP neural network. Experimental result indicates, the optimized BP neural network＇ s constringency speed is faster, and the problem that BP algorithm is easy to be trapped into local optimization has been solved.
出处
《咸宁学院学报》
2005年第6期49-51,共3页
Journal of Xianning University
基金
咸宁学院重点科研资助项目(KL0412)
关键词
遗传算法
神经网络
BP算法
权值优化
Genetic algorithm
Neural networks
BP algorithm
Optimization of weights
