模糊联想记忆网络对模式摄动的鲁棒性分析  

Robustness analysis of fuzzy associative memories with perturbation of sample pattern pairs

作　　者：宋鸾姣[1] 徐蔚鸿[2] 

机构地区：[1]湖南商学院,长沙410205 [2]长沙理工大学计算机与通信工程学院,长沙410077

出　　处：《计算机工程与应用》2007年第11期72-74,112,共4页Computer Engineering and Applications

基　　金：湖南省教育厅科研基金(the research Project of Department of Education of Hunan Province of China under Grant No.04C509)。

摘　　要：在实际问题中,所获取的模糊神经网络的训练模式对总与客观真实的模式对存在一定的小幅误差(摄动),从而可能导致对某些输入网络的实际输出与期望输出有很大的误差。为此,提出了训练模式集摄动对模糊联想记忆网络(FAM)的鲁棒性概念,并具体讨论了采用一种新的权值学习算法时FAM的这种鲁棒性及其控制方法。最后通过实验证明了采用这种新的权值学习算法时,FAM对模式摄动不会拥有好的鲁棒性。In practice,there always is small variance （perturbation） between patterns obtained and objective patterns for fuzzy neural networks,sequentially,there may be big variance（oscillation） between the output of the neural networks and the objective true output for some input.Hereby,the authors propose robustness concept of Fuzzy Associative Memory（FAM for short） with perturbation of sample patterns in the paper.Further,concretely analyze such robustness and the controlling method of FAM using a new weight learning algorithm advanced in the paper.In the end,the authors prove by experiment that the robustness of FAM is not good when using the new weight learning algorithm advanced in the paper.

关 键 词：模糊联想记忆 学习算法 训练模式 摄动 鲁棒 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]