Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Toward an evolvable neuromolecular hardware: a hardware design fbr a multilevel artificial brain with digital circuits
Autore:
Chen, JC; Chen, RD;
Indirizzi:
Natl YunLin Univ Sci & Technol, Dept Management Informat Syst, Touliu 640,Taiwan Natl YunLin Univ Sci & Technol Touliu Taiwan 640 Syst, Touliu 640,Taiwan
Titolo Testata:
NEUROCOMPUTING
, volume: 42, anno: 2002,
pagine: 9 - 34
SICI:
0925-2312(200201)42:<9:TAENHA>2.0.ZU;2-W
Fonte:
ISI
Lingua:
ENG
Soggetto:
MICROTUBULE-ASSOCIATED PROTEINS; VISUAL-PATTERN RECOGNITION; NEURAL NETWORKS; CYCLIC-NUCLEOTIDES; CELLULAR-AUTOMATA; ACTIN-FILAMENTS; ARCHITECTURE; INFORMATION; PRINCIPLE; MEMORY;
Keywords:
evolutionary adaptability; artificial brain; multilevel evolutionary learning; evolvable hardware;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
81
Recensione:
Indirizzi per estratti:
Indirizzo: Chen, JC Natl YunLin Univ Sci & Technol, Dept Management Informat Syst, 123 Univ Rd, Touliu 640, Taiwan Natl YunLin Univ Sci & Technol 123 Univ Rd Touliu Taiwan 640 wan
Citazione:
J.C. Chen e R.D. Chen, "Toward an evolvable neuromolecular hardware: a hardware design fbr a multilevel artificial brain with digital circuits", NEUROCOMPUT, 42, 2002, pp. 9-34

Abstract

A biologically inspired neuromolecular architecture implemented on digitalcircuits is proposed in this paper. Digital machines and biological systems provide different modes of information processing. The former are designed to be effectively programmable, whereas the latter have self-organizing dynamics. Previously, we developed a multilevel computer model that capturesintra- and interneuronal information processing. The experimental results showed that this self-organizing model has long-term evolutionary learning capability that allows it to learn in a continuous manner, and that the function of the system changes as its structure is altered. Malleability and gradual transformability play an important role in facilitating evolutionarylearning. The implementation of this model on digital circuits would allowit to perform on a real-time basis and to provide an architectural paradigm for emerging molecular or neuromolecular electronic technologies. (C) 2002 Elsevier Science B.V. All rights reserved.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 25/01/20 alle ore 03:28:02