摘要
提出了一种新的基于形态学和模糊运算的联想记忆网络———模糊形态学联想记忆网络FMAM(FuzzyMorphologicalAssociativeMemories)。它与经典联想记忆有显著不同。文中分析了FMAM的记忆能力以及抗腐蚀和膨胀噪声的能力。自联想FMAM具有无限存储能力,能保证完全回忆,并且回忆在一步内完成,可模糊性解释等。仿真实验验证了自联想FMAM的良好性能。
Fuzzy morphological associative memories (FMAM) based on morphological and fuzzy operations are presented in this paper. The properties of FMAM are greatly different from those of classical associative memories. FMAM storage capacity and tolerance capability of erosive/dilative noise are analyzed in this paper. Autoassociative FMAM have unlimited storage capacity, perfect recall guarantee, recall in one step and fuzzy explanation. The experimental results prove the effective performance of autoassociative FMAM.
出处
《华东船舶工业学院学报》
2002年第5期28-32,共5页
Journal of East China Shipbuilding Institute(Natural Science Edition)
基金
江苏省青年基金课题资助(院编2000315)
