| 一种用于BP网络优化的并行模拟退火遗传算法 |
| |
| 引用本文： | 刘月娥,何东健,李峥嵘.一种用于BP网络优化的并行模拟退火遗传算法[J].计算机应用,2006,26(1):204-0206. |
| |
| 作者姓名： | 刘月娥 何东健 李峥嵘 |
| |
| 作者单位： | 1. 西北农林科技大学机电工程学院,陕西,杨凌,712100
2. 西北农林科技大学信息工程学院,陕西,杨凌,712100 |
| |
| 摘 要： | 针对模拟退火算法和遗传算法存在的不足，提出了并行模拟退火遗传算法，并用于3层BP神经网络优化。在适应度函数中引入模拟退火机制，采用排序、最优保存策略选择算子、启发式交叉和多点非均匀变异改进遗传算子，利用模拟退火算法产生新解增加搜索方向，并结合并行进化思想对经典遗传算法进行改进。通过对英文字母识别的仿真实验，表明该方法全局搜索能力、局部搜索能力和收敛速度都优于经典遗传算法。
|
| 关 键 词： | BP网络 遗传算法 模拟退火算法 伪并行 |
| 文章编号： | 1001-9081（2006）01-0204-03 |
| 收稿时间： | 2005-07-12 |
| 修稿时间： | 2005-07-122005-08-27 |
Parallel simulated annealing genetic algorithm for optimizing BP neural network |
| |
| LIU Yue-e,HE Dong-jian,LI Zheng-rong.Parallel simulated annealing genetic algorithm for optimizing BP neural network[J].journal of Computer Applications,2006,26(1):204-0206. |
| |
| Authors: | LIU Yue-e HE Dong-jian LI Zheng-rong |
| |
| Abstract: | A Parallel Simulated Annealing Genetic Algorithm(PSAGA) was given for the optimization of 3 levels BP neural network.Simulated annealing(SA) method was applied in fitness scaling,genetic operator was improved by ranking selection which copied the fittest,heuristic crossover and multi nonuniform mutation,and SA was used as the state generator.The idea of parallel evolution was combined into PSAGM.Simulation to recognition of English letters proved PSAGM was better than simple genetic algorithm in global search,local search and speed of convergence. |
| |
| Keywords: | BP network Genetic Algorithm(GA) Simulated Annealing Algorithm(SAA) pseudo-parallel |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用》浏览原始摘要信息 |
|
点击此处可从《计算机应用》下载全文 |
