期刊文献+

基于概率的MAM记忆性能模型 被引量:4

Recall performance model of MAM based on propability
在线阅读 下载PDF
导出
摘要 针对即使输入模式无噪声,形态学联想记忆在用于异联想时仍不能保证完全回忆的问题,借助概率学知识,提出一个概率模型来刻画形态学联想记忆网络的记忆性能。该概率模型能从整体上正确地反映网络的输入端维数、输出端维数以及模式对的数目对形态学联想记忆的记忆性能的影响趋势,对进一步研究与改进形态学联想记忆,有一定的指导意义。 When the morphological associative memories (MAM) are used as the hetero-associative memories, it may be not perfect recall even if input patterns are perfect. Aimed at this problem, the probability model can be built with the probability knowledge to reflect the recall performance of MAM. The probability model correctly reflect the effect trend of the dimension of the input mode, the dimension of the output mode and the number of the pattern pair to the recall performance of MAM on the whole. The results from the research on the recall performance of MAM have guiding significance for the further research and improvement of MAM.
出处 《计算机工程与设计》 CSCD 北大核心 2011年第2期676-680,684,共6页 Computer Engineering and Design
基金 河南省自然科学基金项目(102300410099) 河南师范大学博士基金项目(521662)
关键词 形态学联想记忆 记忆性能 概率模型 异联想 图像的联想识别 morphological associative memories recall performance probability model hetero-associative memories associative recognition for images
作者简介 冯乃勤(1953-),男,河南新乡人,博士,教授,硕士生导师,研究方向为人工智能、神经网络和联想记忆;E-mail:fengnaiqin@163.com 敖连辉(1983-),男,江西新余人,硕士,研究方向为神经网络和联想记忆; 李素娟(1980-),女,河南鹤壁人,硕士,研究方向为神经网络和联想记忆; 赵永进(1980-),男,河南新乡人,硕士,讲师,研究方向为人工神经网络; 董亚杰(1982-),男,河南周口人,硕士,研究方向为智能Agent、网络学习。
  • 相关文献

参考文献21

  • 1Ritter GX,Sussner P, Diaz-de-leon JL.Morphological associative memories [J]. IEEE Trans on Neural Networks, 1998,9 (2): 281-292.
  • 2Hopfield JJ.Neural networks and physical systems with emer- gent collective computational abilities [C]. Proceedings of Na- tional Academic Science,1982,79:2554-2558.
  • 3Kosko B. Bidirectional associative memory [J]. IEEE Trans on SMC,1988,18(1):49-60.
  • 4Ritter GX, Urcid G, Iancu L. Reconstruction of patterns from noisy inputs using morphological associative memories[J].Jour- nal of Mathematical Imaging and Vision,2003,9:95-111.
  • 5Urcid G, Ritter GX. Noise masking for pattern recall using a single lattice matrix auto-associative memory [C]. BC, Canada: IEEE World Congress on Computational Intelligence Vancou- ver,2006:16-21.
  • 6Hattori M,Fukui A,Ito H.A fast method of constructing kernel patterns for morphological associative memories[C].Singapore, China:Proc 9th Int Conf on Neural Information Processing,2002: 1058-1063.
  • 7Urcid G,Ritter GX.Kernel computation in morphological asso- ciative memories for grayscale image recollection[C].Honolulu Hawaii:Proc 5th IASTED Int Confon Signal and Image Proces- sing,2003:450-455.
  • 8Sussner P.Associative morphological memories based on varia- tions of the kernel and dual kernel methods[J] .Neural Networks, 2003(16):625-632.
  • 9Sussner P, Valle ME.Implicative fuzzy associative memories[J]. IEEE T Fuzzy Systems,2006(6):793-807.
  • 10Sussner P, Valle ME.Morphological and certain fuzzy morpho- logical associative memories for classification and prediction [C].Computational Intelligence Based on Lattice Theory,2007: 149-171.

二级参考文献62

共引文献50

同被引文献14

  • 1黄少芳,吴锡生,张凌芳.动态核的形态联想记忆网络在灰度图中的应用[J].微计算机信息,2005,21(12Z):176-178. 被引量:6
  • 2陈蕾,陈松灿,张道强.小世界体系的多对多核联想记忆模型及其应用[J].软件学报,2006,17(2):223-231. 被引量:9
  • 3冉天保,吴锡生.尺度空间的联想记忆网络在灰度图中的应用[J].计算机仿真,2007,24(7):156-159. 被引量:3
  • 4Sussner P. Associative morphological memories based on variations of the kemel [J]. Neural Networks ,2003,4:625 -632.
  • 5Ritter, G. X. , Sussner P. Morphological Associative Memories [ J ]. IEEE Transactions on Neural Networks, 1998,9 ( 2 ) :281 - 292.
  • 6Jeng Y J, Yeh C C, Chiueh T D. Exponential birectional associative memories [ J ]. IEEE Transactions on Neural Networks, 1991, 2(2) :275 -284.
  • 7Gerhard X. Ritter,Gonzalo Urcid,Laurentiu Iancu.Reconstruction of Patterns from Noisy Inputs Using Morphological Associative Memories[J].Journal of Mathematical Imaging and Vision.2003(2)
  • 8Ritter G X,Sussner P,Diaz-de-Leon J L.Morphological associative memories[].IEEE Transactions on Neural Networks.1998
  • 9Gonzalo Urcid,Gerhard X Ritter.Noise Masking for Pattern Recall using a Single Lattice Matrix Auto-Associative Memory[].IEEE World Congress on Computational Intelligence.2006
  • 10Feng Nai-qin,Cao Xi-zheng,Li Sujuan,et al.A New Method of Morphological Associative Memories[].Lecture Notes in Artificial Intelligence.2009

引证文献4

二级引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部