南京理工大学学报（自然科学版）2011，Vol.35Issue(5)：664-669,6.
形态双向联想记忆网络的摄动鲁棒性研究
Perturbation Robustness of Morphological Bidirectional Associative Memories Networks
摘要
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 FMBAM networks is theoretically proved. The simulations show that the MBAM network has good robustness on the perturbation of training pattern pairs, and its rough training pattern pairs are acceptable.Trie FMBAM network robustness is not so good,and its training pattern pairs should have higher accuracy.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Key words
neural networks/morphological bidirectional associative memories/fuzziness/perturbation/training pattern pairs/robustness分类
信息技术与安全科学引用本文复制引用
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):664-669,6.基金项目
华东交通大学科研基础项目(09102018) （09102018）
南京理工大学科研计划项目(ZYTS067) （ZYTS067）
