Compact MOS Implementation of a Reaction-Diffusion CNN

Abstract

A biologically inspired single layer cellular neural network (CNN) with trigger wave formation capability is presented. A novel compact MOS cell circuit is proposed which exhibits a third order I-V characteristic with negative differential resistance (NDR). Certain D.C. characteristics of both the proposed cell and the network are described and corresponding theoretical estimations are presented. It is shown that the CNN formed by resistive coupling of these cells has very low complexity and realizes a reaction-diffusion system. The dynamical network behavior is demonstrated by transient simulations of a 2D cell array at the circuit level.

Periodically intermittent sampled-data control of a class of diffusion neural networks

“…For example, the reaction-diffusion cellular neural networks introduced in [13] have found several applications in artificial locomotion, image processing, shortest path solution and pattern recognition ( [14]). Thus, it is of importance to study the diffusion effects on stability and stabilization of neural networks.…”

Adaptive Stabilizer Design of Reaction-Diflusion Neural Networks With Time-varying Delays

“…And reaction-diffusion neural networks (RDNNs) appear to possess potential applications in image processing, artificial locomotion [3], motion control [4], and so on. Moreover, they can be implemented by very large-scale integrated (VLSI) electronic circuits [4,5]. Therefore, it is important and, in effect, necessary to study and understand deeply phenomena of neural network models under both space and time variations.…”