模糊形态学双向联想记忆网络的性质  

Properties of Fuzzy Morphological Bidirectional Associative Memories

作　　者：曾水玲[1,2] 徐蔚鸿[2,3] 杨静宇[2] 

机构地区：[1]吉首大学信息科学与工程学院,吉首416000 [2]南京理工大学计算机科学与技术学院,南京210094 [3]长沙理工大学计算机与通信工程学院,长沙410077

出　　处：《模式识别与人工智能》2012年第1期54-62,共9页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金项目(No.60632050);湖南省教育厅科研基金青年项目(No.10B088);吉首大学博士基金项目(No.jsdxxcfxbskyxm201117)资助

摘　　要：为模糊形态学双向联想记忆网络(FMBAM)提出一个学习算法.在理论上证明只要存在使给定的模式对集合成为FMBAM的平衡态集合,则该学习算法总能计算出相应的最大连接权矩阵对.该最大连接权矩阵对能使FMBAM对任意输入在一步内就进入平衡态,并且神经网络全局收敛到平衡态.FMBAM的每个平衡态都是Lya-punov稳定的.当训练模式存在摄动时,利用该学习算法训练的FMBAM,对训练模式摄动拥有好的鲁棒性.A learning algorithm is proposed for a class of fuzzy morphological bidirectional associative memories（FMBAM）.It is proved theoretically that,for any given set of pattern pairs,if existing pairs of connection weight matrices which make the set become a set of the equilibrium states of FMBAM,the proposed learning algorithm can give the maximum of all such pairs of weight matrices.And the learning algorithm ensure that the FMBAM with this maximal pair of connection weight matrices can be convergent to an equilibrium state in one iterative process for any input.Any equilibrium state of FMBAM is Lyapunov stable.FMBAM can converge to equilbrium state for its any input vector.The robustness of FMBAM is good when the learning algorithm is used to train FMBAM and training pattern pairs have perturbations.

关 键 词：模糊形态双向联想记忆网络(FMBAM) 学习算法 稳定性 收敛性 鲁棒性 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]