Abstract
Realization of associative memories by cellular neural networks (CNNs) with binary output is studied. Concerning this problem, a CNN design method based upon generalized eigenvalue minimization (GEVM) has recently been proposed. In this brief, a new CNN design method which is based on the GEVM-based method will be presented. We first give some analytical results related to the basin of attraction of a memory vector. We then derive the design method by combining these analytical results and the GEVM-based method. We finally show through computer simulations that the proposed method can achieve higher recall probability than the original GEVM-based method.
| Original language | English |
|---|---|
| Pages (from-to) | 1569-1574 |
| Number of pages | 6 |
| Journal | IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications |
| Volume | 50 |
| Issue number | 12 |
| DOIs | |
| Publication status | Published - Dec 2003 |
| Externally published | Yes |
Fingerprint
Keywords
- Associative memory
- Basin of attraction
- Cellular neural networks (CNNs)
- Generalized eigenvalue minimization (GEVM)
ASJC Scopus subject areas
- Electrical and Electronic Engineering
Cite this
An improvement of the design method of cellular neural networks based on generalized eigenvalue minimization. / Bise, Ryoma; Takahashi, Norikazu; Nishi, Tetsuo.
In: IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, Vol. 50, No. 12, 12.2003, p. 1569-1574.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - An improvement of the design method of cellular neural networks based on generalized eigenvalue minimization
AU - Bise, Ryoma
AU - Takahashi, Norikazu
AU - Nishi, Tetsuo
PY - 2003/12
Y1 - 2003/12
N2 - Realization of associative memories by cellular neural networks (CNNs) with binary output is studied. Concerning this problem, a CNN design method based upon generalized eigenvalue minimization (GEVM) has recently been proposed. In this brief, a new CNN design method which is based on the GEVM-based method will be presented. We first give some analytical results related to the basin of attraction of a memory vector. We then derive the design method by combining these analytical results and the GEVM-based method. We finally show through computer simulations that the proposed method can achieve higher recall probability than the original GEVM-based method.
AB - Realization of associative memories by cellular neural networks (CNNs) with binary output is studied. Concerning this problem, a CNN design method based upon generalized eigenvalue minimization (GEVM) has recently been proposed. In this brief, a new CNN design method which is based on the GEVM-based method will be presented. We first give some analytical results related to the basin of attraction of a memory vector. We then derive the design method by combining these analytical results and the GEVM-based method. We finally show through computer simulations that the proposed method can achieve higher recall probability than the original GEVM-based method.
KW - Associative memory
KW - Basin of attraction
KW - Cellular neural networks (CNNs)
KW - Generalized eigenvalue minimization (GEVM)
UR - http://www.scopus.com/inward/record.url?scp=0742304101&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0742304101&partnerID=8YFLogxK
U2 - 10.1109/TCSI.2003.819827
DO - 10.1109/TCSI.2003.819827
M3 - Article
AN - SCOPUS:0742304101
VL - 50
SP - 1569
EP - 1574
JO - IEEE Transactions on Circuits and Systems I: Regular Papers
JF - IEEE Transactions on Circuits and Systems I: Regular Papers
SN - 1057-7122
IS - 12
ER -