| 利用遗传算法优化人工神经网络权值 |
| |
| 引用本文： | 阮若林.利用遗传算法优化人工神经网络权值[J].咸宁学院学报,2005,25(6):49-51. |
| |
| 作者姓名： | 阮若林 |
| |
| 作者单位： | 咸宁学院,信息工程学院,湖北,咸宁,437005 |
| |
| 基金项目： | 咸宁学院重点科研资助项目（KL0412） |
| |
| 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．
|
| 关 键 词： | 遗传算法 神经网络 BP算法 权值优化 |
| 文章编号： | 1006-5342（2005）06-0049-03 |
| 收稿时间： | 10 21 2005 12:00AM |
| 修稿时间： | 2005-10-21 |
Application of Genetic Algorithm in Artificial Neural Network Weights Optimizing |
| |
| RUAN Ruo-lin.Application of Genetic Algorithm in Artificial Neural Network Weights Optimizing[J].Journal of Xianning College,2005,25(6):49-51. |
| |
| Authors: | RUAN Ruo-lin |
| |
| Institution: | School of Information and Engineering,Xianning College ,Xianning 437005, China |
| |
| Abstract: | 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. |
| |
| Keywords: | Genetic algorithm Neural networks BP algorithm Optimization of weights |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
