首页 | 本学科首页   官方微博 | 高级检索  
     

形态双向联想记忆网络的摄动鲁棒性研究
引用本文:何春梅,叶征春,韩牟,叶有培. 形态双向联想记忆网络的摄动鲁棒性研究[J]. 南京理工大学学报(自然科学版), 2011, 35(5)
作者姓名:何春梅  叶征春  韩牟  叶有培
作者单位:1. 华东交通大学信息工程学院,江西南昌,330013
2. 华东交通大学机电工程学院,江西南昌,330013
3. 南京理工大学计算机科学与技术学院,江苏南京,210094
基金项目:华东交通大学科研基础项目(09102018); 南京理工大学科研计划项目(ZYTS067)
摘    要:针对训练模式对的小幅摄动可能会对神经网络的输出产生副作用的问题,该文研究了形态双向联想记忆(MBAM)网络和模糊形态双向联想记忆(FMBAM)网络训练模式对的摄动鲁棒性。比较了训练模式对摄动前后2种网络输出范围的变化,理论证明了MBAM和FMBAM 2种网络的摄动鲁棒性。理论和仿真实例表明:MBAM网络对训练模式对的摄动全局拥有好的鲁棒性,其训练模式对的选取可以适度粗糙;而FMBAM网络对训练模式对的摄动不具有好的鲁棒性,则其训练模式对的选取精度要求较高。

关 键 词:神经网络  形态双向联想记忆  模糊  摄动  训练模式对  鲁棒性  

Perturbation Robustness of Morphological Bidirectional Associative Memories Networks
HE Chun-mei,YE Zheng-chun,HAN Mu,YE You-pei. Perturbation Robustness of Morphological Bidirectional Associative Memories Networks[J]. Journal of Nanjing University of Science and Technology(Nature Science), 2011, 35(5)
Authors:HE Chun-mei  YE Zheng-chun  HAN Mu  YE You-pei
Affiliation:HE Chun-mei1,YE Zheng-chun2,HAN Mu3,YE You-pei3(1.School of Information Engineering,2.School of Mechanical and Electronical Engineering,East China Jiaotong University,Nanchang 330013,China,3.School of Computer Science and Technology,NUST,Nanjing 210094,China)
Abstract:In view of the problem that the small perturbations of training pattern pairs may cause side effects on the outputs of neural networks,the influences of perturbations of training pattern pairs on the morphological bidirectional associative memories(MBAM)networks and fuzzy morphological bidirectional associative memories(FMBAM)networks are researched here.By comparing the output variations of the two training sample pairs before and after perturbations,the perturbation robustness of the MBAM networks and FMB...
Keywords:neural networks  morphological bidirectional associative memories  fuzziness  perturbation  training pattern pairs  robustness  
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号