Zj. Lu et Dr. Liu, A new synthesis procedure for a class of cellular neural networks with space-invariant cloning template, IEEE CIR-II, 45(12), 1998, pp. 1601-1605
Citations number
15
Categorie Soggetti
Eletrical & Eletronics Engineeing
Journal title
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-ANALOG AND DIGITAL SIGNAL PROCESSING
This paper presents a new synthesis procedure (design algorithm) for cellul
ar neural networks (CNN's) with a space-invariant cloning template with app
lications to associative memories. In the present synthesis procedure, the
design problem is formulated as a set of linear inequalities, and the inequ
alities are solved using the well-known perceptron training algorithm. When
desired memory patterns are given by a set of bipolar vectors, it is guara
nteed that a cellular neural network with a space-invariant cloning templat
e can be designed using the design algorithm developed herein. An algorithm
is also provided to design CNN's with space-invariant cloning templates an
d with symmetric connection matrices to guarantee the global stability of t
he network. Two specific examples are included to demonstrate the applicabi
lity of the methodology developed herein.