A synthesis procedure for associative memories based on space-varying cellular neural networks
- Authors
- Park, J; Kim, HY; Park, Y; Lee, SW
- Issue Date
- 1월-2001
- Publisher
- PERGAMON-ELSEVIER SCIENCE LTD
- Keywords
- associative memory; cellular neural network; generalized eigenvalue problem; linear matrix inequality problem
- Citation
- NEURAL NETWORKS, v.14, no.1, pp.107 - 113
- Indexed
- SCIE
SCOPUS
- Journal Title
- NEURAL NETWORKS
- Volume
- 14
- Number
- 1
- Start Page
- 107
- End Page
- 113
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/124401
- DOI
- 10.1016/S0893-6080(00)00086-1
- ISSN
- 0893-6080
- Abstract
- In this paper, we consider the problem of realizing associative memories via space-varying CNNs (cellular neural networks). Based on some known results and a newly derived theorem fur the CNN model, we propose a synthesis procedure for obtaining a space-varying CNN that can store given bipolar vectors with certain desirable properties. The major part of our synthesis procedure consists of solving generalized eigenvalue problems and/or linear matrix inequality problems, which can be efficiently solved by recently developed interior point methods. The validity of the proposed approach is illustrated by a design example. (C) 2001 Elsevier Science Ltd. All rights reserved.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School > Department of Artificial Intelligence > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.