Title :
On discrete-time cellular neural networks for associative memories
Author :
Grassi, Giuseppe
Author_Institution :
Dipt. di Ingegneria dell´´Innovazione, Lecce Univ., Italy
fDate :
1/1/2001 12:00:00 AM
Abstract :
In this paper, discrete-time cellular neural networks (DTCNNs) with a globally asymptotically stable equilibrium point, are designed to behave as associative memories. The objective is achieved by considering feedback parameters related to circulant matrices and by satisfying frequency domain stability criteria. The approach, by generating DTCNNs where the input data are fed via external inputs rather than initial conditions, enables both heteroassociative and autoassociative memories to be designed. Numerical examples are reported in order to show the capabilities of the proposed tool
Keywords :
asymptotic stability; cellular neural nets; content-addressable storage; discrete time systems; feedback; stability criteria; associative memories; autoassociative memories; cellular neural networks; circulant matrices; discrete-time CNN; feedback parameters; frequency domain stability criteria; globally asymptotically stable equilibrium point; heteroassociative memories; Associative memory; Cellular neural networks; Circuits; Design methodology; Frequency domain analysis; Hardware; Neural networks; Neurofeedback; Stability criteria; Steady-state;
Journal_Title :
Circuits and Systems I: Fundamental Theory and Applications, IEEE Transactions on
