Nov 9, 2000
A Design Method of Cellular Neural Networks with Symmetric Connections for Associative Memories
Technical report of IEICE. CST
- ,
- ,
- Volume
- 100
- Number
- 418
- First page
- 17
- Last page
- 22
- Language
- Japanese
- Publishing type
- Publisher
- The Institute of Electronics, Information and Communication Engineers
This report deals with the problem of designing cellular neural networks (CNNs) for associative memories. Concerning the problem, a design method of sparsely connected neural networks by means of the singular value decomposition has been proposed, and we can design CNNs by using this method. However this method has a problem that the complete stability of a designed CNN is not guarateed because the CNN has non-symmetric connections in general. In this report, we give a new design method of CNNs which guarantees the symmetry of connections. Any CNN designed by our method is completely stable, because it has been proved that a CNN with symmetric connections is completely stable.
- Link information
-
- CiNii Articles
- http://ci.nii.ac.jp/naid/110003300180
- CiNii Books
- http://ci.nii.ac.jp/ncid/AN10438446
- URL
- http://id.ndl.go.jp/bib/5603046
- ID information
-
- ISSN : 0913-5685
- CiNii Articles ID : 110003300180
- CiNii Books ID : AN10438446