|
|||||
|
|
| 利用人工鱼群算法优化前向神经网络 | |
| 引用本文： | 马建伟,张国立,谢宏,周春雷,王晶.利用人工鱼群算法优化前向神经网络[J].计算机应用,2004,24(10):21-23. |
| 作者姓名： | 马建伟 张国立 谢宏 周春雷 王晶 |
| 作者单位： | 1. 华北电力大学,计算机科学与工程系,河北,保定,071003 2. 华北电力大学,应用数学系,河北,保定,071003 3. 上海海事大学,电子工程系,上海,200135 |
| 摘 要： | 人工鱼群算法(AFSA)是一种最新提出的新型的寻优策略，文中尝试将人工鱼群算法用于三层前向神经网络的训练过程，建立了相应的优化模型，进行了实际的编程计算，并与加动量项的BP算法、演化算法以及模拟退火算法进行比较，结果表明AFSA具有鲁棒性强，全局收敛性好，以及对初值的不敏感性等特点。 |
| 关 键 词： | 人工鱼群算法 前向神经网络 随机搜索 |
| 文章编号： | 1001-9081(2004)10-0021-03 |
Optimization of feed-forward neural networks based on artificial fish-swarm algorithm |
|
| MA Jian-wei,ZHANG Guo-li,XIE Hong,ZHOU Chun-lei,WANG Jing.Optimization of feed-forward neural networks based on artificial fish-swarm algorithm[J].journal of Computer Applications,2004,24(10):21-23. | |
| Authors: | MA Jian-wei ZHANG Guo-li XIE Hong ZHOU Chun-lei WANG Jing |
| Affiliation: | MA Jian-wei~1,ZHANG Guo-li~2,XIE Hong~3,ZHOU Chun-lei~1,WANG Jing~1 |
| Abstract: | Artificial Fish-swarm Algorithm(AFSA) is a novel optimizing method proposed lately.An Artificial Fish-swarm Algorithm(AFSA) for the optimization of feed-forward neural networks and a model based on this method were presented for the first time here.Compared with the Back-propagation Algorithm added momentum,the Evolve Algorithm and the Simulated Anncaling Algorithm,optimization result of feed-forward neural networks by AFSA demonstrates that AFSA has a strong robustness and good global astringency.AFSA is also proved to be insensitive to initial values. |
| Keywords: | artificial fish-swarm algorithm feed-forward neural networks random search |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |
