Evolvable cellular classifiers

Author

Kang, Hoon

Author_Institution

Sch. of Electr. & Electron. Eng., Chung-Ang Univ., Seoul, South Korea

Volume

1

fYear

2000

fDate

2000

Firstpage

464

Abstract

Cellular automata are well-known for their self-organizing and dynamic behaviors in the field of artificial life. This paper addresses a new neuronic architecture, called an evolvable cellular classifier, which evolves by means of genetic rules (chromosomes) in nonuniform cellular automata. An evolvable cellular classifier is primarily based on cellular programming, but its mechanism is simpler because it utilizes only mutations for its main genetic operators, and it resembles the Hopfield network. Therefore, desirable bit patterns can be obtained through evolutionary processes for just one individual agent. As a result, evolvable hardware is derived which is applicable to the classification of bit-string information

Keywords

Hopfield neural nets; artificial life; cellular automata; mathematical operators; pattern classification; Hopfield network; artificial life; bit patterns; bit-string information classification; cellular programming; chromosomes; evolvable cellular classifiers; evolvable hardware; genetic operators; genetic rules; mutations; neuronic architecture; nonuniform cellular automata; self-organizing dynamic behavior; Automata; Automatic programming; Biological cells; Cellular networks; Chaos; Genetic mutations; Hardware; Lattices; Organizing;

fLanguage

English

Publisher

ieee

Conference_Titel

Evolutionary Computation, 2000. Proceedings of the 2000 Congress on

Conference_Location

La Jolla, CA

Print_ISBN

0-7803-6375-2

Type

conf

DOI

10.1109/CEC.2000.870333

Filename

870333