Properties of Fuzzy Morphological Bidirectional Associative Memories
ZENG Shui-Ling1,2, XU Wei-Hong2,3, YANG Jing-Yu2
1.College of Information Science and Engineering,Jishou University,Jishou 416000 2.College of Computer Science and Technology,Nanjing University of Science and Technology,Nanjing 210094 3.College of Computer and Communications Engineering,Changsha University of Science and Technology,Changsha 410077
Abstract: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.
[1] Ritter G X,Diaz-de-Leon J L,Sussner P.Morphological Bidirectional Associative Memories.Neural Networks,1999,12(6): 851-867 [2] Kosko B.Bidirectional Associative Memory.IEEE Trans on Systems,Man and Cybernetics,1988,18(1): 49-60 [3] Cheng Qiansheng,Fan Zhoutian.The Stability Problem for Fuzzy Bi-Directional Associative Memories.Fuzzy Sets and Systems,2002,132(1): 83-90 [4] Lou Xuyang,Cui Baotong.Robust Asymptotic Stability of Uncertain Fuzzy BAM Neural Networks with Time-Varying Delays.Fuzzy Sets and Systems,2007,158(24): 2746-2756 [5] Ali M S,Balasubramaniam P.Exponential Stability of Uncertain Stochastic Fuzzy BAM Neural Networks with Time-Varying Delays.Neurocomputing,2009,72(4/5/6): 1347-1354 [6] Liu Bin,Shi Peng.Delay-Range-Dependent Stability for Fuzzy BAM Neural Networks with Time-Varying Delays.Physics Letters A,2009,373(21): 1830-1838 [7] Han S C,Gu Yundong,Li Hongxing.An Application of Incline Matrices in Dynamic Analysis of Generalized Fuzzy Bidirectional Associative Memories.Fuzzy Sets and Systems,2007,158(12): 1340-1347 [8] Ritter G X,Sussner P,Diaz-de-Leon J L.Morphological Associative Memories.IEEE Trans on Neural Networks,1998,9(2): 281-293 [9] Wang S T,Lu H J.On New Fuzzy Morphological Associative Memories.IEEE Trans on Fuzzy Systems,2004,12(3): 316-323 [10] Wang Min,Wang Shitong,Wu Xiaojun.Initial Results on Fuzzy Morphological Associative Memories.Acta Electronica Sinica,2003,31(5): 690-693 (in Chinese) (王 敏,王士同,吴小俊.新模糊形态学联想记忆网络的初步研究.电子学报,2003,31(5): 690-693) [11] Sussner P.Associative Morphological Memories Based on Variations of the Kernel and Dual Kernel Methods.Neural Networks,2003,16(5/6): 625-632 [12] Gader P D,Khabou M A,Koldobsky A.Morphological Regularization Neural Networks.Pattern Recognition,2000,33(6): 935-944 [13] Wu Xisheng,Wang Shitong.Bi-Directional Fuzzy Morphological Associative Memory and Its Robust Analysis for Random Noise.Pattern Recognition and Artificial Intelligence,2005,18(3): 257-262 (in Chinese) (吴锡生,王士同.双向模糊形态联想记忆网络及其抗随机噪声的研究.模式识别与人工智能,2005,18(3): 257-262) [14] Xu Weihong,Song Luanjiao,Li Aihua,et al.Influences and Control of Perturbations of Training Pattern Pairs on Fuzzy Bidirectional Associative Memories.Chinese Journal of Computers,2006,29(2): 153-157 (in Chinese) (徐蔚鸿,宋鸾姣,李爱华,等.训练模式对的摄动对模糊双向联想记忆网络的影响及其控制.计算机学报,2006,29(2): 153-157) [15] Zeng Shuiling,Xu Weihong,Yang Jingyu.Influences of Perturbations of Training Pattern Pairs on Fuzzy Morphological Associative Memory Networks.Pattern Recognition and Artificial Intelligence,2010,23(1): 91-96 (in Chinese) (曾水玲,徐蔚鸿,杨静宇.训练模式摄动对模糊形态学联想记忆网络的影响.模式识别与人工智能,2010,23(1): 91-96)