模式识别与人工智能
Thursday, Apr. 3, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2010, Vol. 23 Issue (1): 91-96    DOI:
Orignal Article Current Issue| Next Issue| Archive| Adv Search |
Influences of Perturbations of Training Pattern Pairs on Fuzzy Morphological Associative Memory Networks
ZENG Shui-Ling1,2,XU Wei-Hong1,2,YANG Jing-Yu1
1.College of Computer Science and Technology,Nanjing University of Science and Technology,Nanjing 210094
2.College of Mathematics and Computer Science,Jishou University,Jishou 416000

Download: PDF (353 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Two kinds of morphological associative memory networks are analyzed by scholars and they have almost the same good fault-tolerant abilities of erosive/dilative noise. In this paper, the investigation reveals that two kinds of networks have different robustness to perturbation of training patterns. The robustness is good to one kind of fuzzy morphological associative memory network, and the property of the other kind is relatively poor. The conclusions offer guidance for the learning algorithm selection of the neural networks and the acquisition process of the previous training patterns.
Key wordsFuzzy Morphological Associative Memory Network      Learning Algorithm      Training Pattern Pair      Perturbation      Robustness     
Received: 12 May 2008     
ZTFLH: TP181  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:   
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2010/V23/I1/91
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn