An Improved Attention Parameter Setting Algorithm Based on Award Learning Mechanism  

作　　者：Fang Xiuduan Liu Binhan Wang Weizhi 

机构地区：[1]Department of Computer Science and Technology, Fuzhou Universtiy, Fujian 350002 Department of Computer Science and Technology, Fuzhou Universtiy, Fujian 350002 Department of Computer Science and Technology, Fuzhou Universtiy, Fujian 350002

出　　处：《计算机科学》2002年第z2期195-197,共3页Computer Science

基　　金：Supported by Fujian Natural Science Foundation(A0110010).

摘　　要：The setting of attention parameters plays a role in the performance of synergetic neural network based on PFAP model. This paper first analyzes the attention parameter setting algorithm based on award-penalty learning mechanism. Then, it presents an improved algorithm to overcome its drawbacks. The experimental results demonstrate that the novel algorithm is better than the original one under the same circumstances.

关 键 词：Synergetic NEURAL Network(SNN)  ATTENTION parameter  Award-penalty LEARNING MECHANISM 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]