Evolutionary modular neural networks for intelligent systems

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The evolutionary approach to artificial neural networks has been rapidly developing in recent years and shows great potential as a powerful tool. However, most evolutionary neural networks have paid little attention to the fact that they can evolve from modules. This paper presents a hybrid method of modular neural networks and evolutionary algorithm as a promising model for intelligent systems. To build a neural network system that is rich in autonomy and creativity, some ideas of artificial life have been adopted. This paper describes the concepts and methodologies for the evolvable model of modular neural networks, which might not only develop spontaneously new functionality, but also grow and evolve its own structure autonomously. We show the potential of the method by applying it to a visual categorization task with handwritten digits. The evolutionary mechanism has shown a strong potential to generate useful network architectures from an initial set of randomly connected networks.

Original languageEnglish
Pages (from-to)483-493
Number of pages11
JournalInternational Journal of Intelligent Systems
Volume13
Issue number6
DOIs
Publication statusPublished - 1998 Jan 1

Fingerprint

Evolutionary Neural Networks
Modular Neural Networks
Intelligent systems
Intelligent Systems
Neural networks
Artificial Life
Network Algorithms
Network Architecture
Categorization
Hybrid Method
Digit
Artificial Neural Network
Evolutionary Algorithms
Neural Networks
Module
Methodology
Model
Network architecture
Evolutionary algorithms
Autonomy

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Human-Computer Interaction
  • Artificial Intelligence

Cite this

@article{9c90b48f027047fda218fe7639137afc,
title = "Evolutionary modular neural networks for intelligent systems",
abstract = "The evolutionary approach to artificial neural networks has been rapidly developing in recent years and shows great potential as a powerful tool. However, most evolutionary neural networks have paid little attention to the fact that they can evolve from modules. This paper presents a hybrid method of modular neural networks and evolutionary algorithm as a promising model for intelligent systems. To build a neural network system that is rich in autonomy and creativity, some ideas of artificial life have been adopted. This paper describes the concepts and methodologies for the evolvable model of modular neural networks, which might not only develop spontaneously new functionality, but also grow and evolve its own structure autonomously. We show the potential of the method by applying it to a visual categorization task with handwritten digits. The evolutionary mechanism has shown a strong potential to generate useful network architectures from an initial set of randomly connected networks.",
author = "Sung-Bae Cho",
year = "1998",
month = "1",
day = "1",
doi = "10.1002/(SICI)1098-111X(199806)13:6<483::AID-INT4>3.0.CO;2-H",
language = "English",
volume = "13",
pages = "483--493",
journal = "International Journal of Intelligent Systems",
issn = "0884-8173",
publisher = "John Wiley and Sons Ltd",
number = "6",

}

Evolutionary modular neural networks for intelligent systems. / Cho, Sung-Bae.

In: International Journal of Intelligent Systems, Vol. 13, No. 6, 01.01.1998, p. 483-493.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Evolutionary modular neural networks for intelligent systems

AU - Cho, Sung-Bae

PY - 1998/1/1

Y1 - 1998/1/1

N2 - The evolutionary approach to artificial neural networks has been rapidly developing in recent years and shows great potential as a powerful tool. However, most evolutionary neural networks have paid little attention to the fact that they can evolve from modules. This paper presents a hybrid method of modular neural networks and evolutionary algorithm as a promising model for intelligent systems. To build a neural network system that is rich in autonomy and creativity, some ideas of artificial life have been adopted. This paper describes the concepts and methodologies for the evolvable model of modular neural networks, which might not only develop spontaneously new functionality, but also grow and evolve its own structure autonomously. We show the potential of the method by applying it to a visual categorization task with handwritten digits. The evolutionary mechanism has shown a strong potential to generate useful network architectures from an initial set of randomly connected networks.

AB - The evolutionary approach to artificial neural networks has been rapidly developing in recent years and shows great potential as a powerful tool. However, most evolutionary neural networks have paid little attention to the fact that they can evolve from modules. This paper presents a hybrid method of modular neural networks and evolutionary algorithm as a promising model for intelligent systems. To build a neural network system that is rich in autonomy and creativity, some ideas of artificial life have been adopted. This paper describes the concepts and methodologies for the evolvable model of modular neural networks, which might not only develop spontaneously new functionality, but also grow and evolve its own structure autonomously. We show the potential of the method by applying it to a visual categorization task with handwritten digits. The evolutionary mechanism has shown a strong potential to generate useful network architectures from an initial set of randomly connected networks.

UR - http://www.scopus.com/inward/record.url?scp=0032098656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032098656&partnerID=8YFLogxK

U2 - 10.1002/(SICI)1098-111X(199806)13:6<483::AID-INT4>3.0.CO;2-H

DO - 10.1002/(SICI)1098-111X(199806)13:6<483::AID-INT4>3.0.CO;2-H

M3 - Article

AN - SCOPUS:0032098656

VL - 13

SP - 483

EP - 493

JO - International Journal of Intelligent Systems

JF - International Journal of Intelligent Systems

SN - 0884-8173

IS - 6

ER -