Integrated circuit emulation of ART1 networks
Arun Rao, Mark R. Walker, Lawrence T. Clark, Lex A. Akers · International Conference on Artificial Neural Networks · 1989
Adaptive resonance theory (ART) is a neural-network based clustering method developed by G.A. Carpenter and S. Grossberg (1987). Its inspiration is neurobiological and its component parts are intended to model a variety of hierarchical inference levels in the human brain. Neural networks based upon ART are capable of recognizing patterns close to previously stored patterns according to some criterion, and storing patterns which are not close to already stored patterns. There are two varieties of ART networks; ART1 recognizes binary inputs and ART2 can deal with general analog inputs. The theory of the networks is outlined, and then hardware implementations are discussed. A pipelined associative memory appears to offer an attractive interim solution to the variety of problems that ART1 addresses. It has the advantage of using the best of conventional technology while being capable of all the functions of a nonparallel hardware implementation of ART1.