节点文献

利用人工鱼群算法优化前向神经网络

Optimization of feed-forward neural networks based on artificial fish-swarm algorithm

推荐 CAJ下载
PDF下载
不支持迅雷等下载工具，请取消加速工具后下载。

【Author】 MA Jian-wei~1,ZHANG Guo-li~2,XIE Hong~3,ZHOU Chun-lei~1,WANG Jing~1(1.Department of Computer Science and Engineering,North China Electric Power University,Baoding Hebei 071003,China;2.Department of Applied Mathematics,North China Electric Power University,Baoding Hebei 071003,China;3.Department of Electronic Engineering,Shanghai Maritime University,Shanghai 200135,China)

【机构】华北电力大学计算机科学与工程系；华北电力大学应用数学系；上海海事大学电子工程系；华北电力大学计算机科学与工程系河北保定071003；河北保定071003；上海200135；河北保定071003；河北保定071003；

【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。更多还原

【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.更多还原

【关键词】人工鱼群算法；前向神经网络；随机搜索；
【Key words】 artificial fish-swarm algorithm； feed-forward neural networks； random search；

【文献出处】计算机应用 ,Computer Applications , 编辑部邮箱 ,2004年10期

【分类号】TP183
【被引频次】111
【下载频次】805

知网节下载

节点文献中：

本文链接的文献网络图示:

本文的引文网络

节点文献