CIRCUIT SIMULATION OF ADAPTIVE RESONANCE THEORY (ART) NEURAL NETWORK USING PSPICE

Author(s): Georgiopoulos, M. | Liou, J.J. | Wuerz, D. |

Year: 1994

Citation: INTERNATIONAL JOURNAL OF ELECTRONICS Volume: 74 Issue: 1 Pages: 101-110

Abstract: This paper outlines the design and simulation of an analogue integrated circuit for the adaptive resonanace theory (ART1) neural network. The circuit is designed based on a set of coupled differential equations which describe the behaviour of the neural network and on analogue electronic components such as operational amplifiers. It performs the same functionality as the one-node neural network in the F2 layer of ART1. We have implemented and verified the circuit using a circuit simulator called Pspice run on a SPARC II Sun workstation. Results obtained from circuit simulation compare favourably with those calculated directly from the coupled differential equations. The one-node circuit developed here can be used as a subcircuit for a larger ART1 neural network with an arbitrary number of nodes.

Topics: Neural Hardware, Models: ART 1,

PDF download




Cross References