Title

Analog Circuit-Design And Implementation Of An Adaptive Resonance Theory (Art) Neural-Network Architecture

Authors

Authors

C. S. Ho; J. J. Liou; M. Georgiopoulos; G. L. Heileman;C. Christodoulou

Comments

Authors: contact us about adding a copy of your work at STARS@ucf.edu

Abbreviated Journal Title

Int. J. Electron.

Keywords

PATTERN-RECOGNITION; Engineering, Electrical & Electronic

Abstract

An analogue circuit implementation is presented for an adaptive resonance theory neural network architecture, called the augmented ART-1 neural network (AARTI-NN). The AARTI-NN is a modification of the popular ARTI-NN, developed by Carpenter and Grossberg, and it exhibits the same behaviour as the ART1-NN. The AART1-NN is a real-time model, and has the ability to classify an arbitrary set of binary input patterns into different clusters. The design of the AARTI-NN circuit is based on a set of coupled nonlinear differential equations that constitute the AARTI-NN model. The circuit is implemented by utilizing analogue electronic components such as operational amplifiers, transistors, capacitors, and resistors. The implemented circuit is verified using the PSpice circuit simulator, running on Sun workstations. Results obtained from the PSpice circuit simulation compare favourably with simulation results produced by solving the differential equations numerically. The prototype system developed here can be used as a building block for larger AARTI-NN architectures, as well as for other types of ART architectures that involve the AARTI-NN model.

Journal Title

International Journal of Electronics

Volume

76

Issue/Number

2

Publication Date

1-1-1994

Document Type

Article

Language

English

First Page

271

Last Page

291

WOS Identifier

WOS:A1994MX99600010

ISSN

0020-7217

Share

COinS