Multiplierless digital learning algorithm for cellular neural networks

Citation
R. Perfetti et G. Costantini, Multiplierless digital learning algorithm for cellular neural networks, IEEE CIRC-I, 48(5), 2001, pp. 630-635
Citations number
11
Categorie Soggetti
Eletrical & Eletronics Engineeing
Journal title
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS
ISSN journal
10577122 → ACNP
Volume
48
Issue
5
Year of publication
2001
Pages
630 - 635
Database
ISI
SICI code
1057-7122(200105)48:5<630:MDLAFC>2.0.ZU;2-7
Abstract
A new learning algorithm is proposed for space-varying cellular neural netw orks, used to implement associative memories. The algorithm exhibits some p eculiar features which make it very attractive: the finite precision of con nection weights is automatically taken into account as a design constraint; no multiplication is needed for weight computation; learning can be implem ented in fixed point digital hardware or simulated on a digital computer wi thout numerical errors.