WNN Optimization Design Based on Artificial Fish-Swarm Algorithm

摘要：

The problem such as parameters initialization and network structure determination is collectively referred to as the WNN optimization design. Aiming at the effect on the performance of WNN, an optimization design algorithm, which is based on Artificial FishSwarm Algorithm(AFSA), is proposed. The AFSA can synchronously determine the initial values of parameters and hidden layer nodes number in search space. The simulation results show it is an effective algorithm, which not only has higher accuracy and faster convergence rate but also can avoid the blindness of the WNN optimization design.

关键词： wavelet neural network(WNN) artificial fish-swarm algorithm(AFSA) optimization design

作者: Tang Xueqin Jin Liya Duanmu Jingshun Xu Zongchang

作者单位: Department of Technology Support Engineerinj Academy of Armored Force Engineering Beijing, China Department of Information Engineering Academy of Armored Force Engineering Beijing, China Department of Equipment Management, College of Engineering, Air Force Engineering University Xian, Department of Technology Support Engineering Academy of Armored Force Engineering Beijing, China

会议类型: 国际会议

会议名称: 2011 International Conference on Computer Science and Network Technology(2011计算机科学与网络技术国际会议 ICCSNT 2011)

会议地点: 哈尔滨

会议语种:英文

页码: 2747-2750

在线出版日期: 2011-12-24（万方平台首次上网日期，不代表论文的发表时间）