Cellular Neural Networks (CNN's) with space-varying inter-connections are considered here to implement associative memories. A fast learning method is presented to compute the interconnection weights. The algorithm was carefully tested and compared to other methods. Storage capacity, noise immunity, and spurious state avoidance capability of the proposed system are discussed.
|Number of pages||5|
|Journal||IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications|
|Publication status||Published - Dec 1 1997|
- Associative memory
- Fixed point
ASJC Scopus subject areas
- Electrical and Electronic Engineering