Modular neural networks evolved by genetic programming

Sung Bae Cho, Katsunori Shimohara

Research output: Contribution to conferencePaper

9 Citations (Scopus)

Abstract

In this paper we present an evolvable model of modular neural networks which are rich in autonomy and creativity. In order to build an artificial neural network which is rich in autonomy and creativity, we have adopted the ideas and methodologies of Artificial Life. This paper describes the concepts and methodologies for the evolvable model of modular neural networks, which will be able not only to develop new functionality spontaneously but also to grow and evolve its own structure autonomously. Although the ultimate goal of this model is to design the control system for such behavior-based robots as Khepera, we have attempted to apply the mechanism to a visual categorization task with handwritten digits. The evolutionary mechanism has shown a strong possibility to generate useful network architectures from an initial set of randomly-connected networks.

Original languageEnglish
Pages681-684
Number of pages4
Publication statusPublished - 1996 Jan 1
EventProceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96 - Nagoya, Jpn
Duration: 1996 May 201996 May 22

Other

OtherProceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96
CityNagoya, Jpn
Period96/5/2096/5/22

Fingerprint

Genetic programming
Neural networks
Network architecture
Robots
Control systems

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Cho, S. B., & Shimohara, K. (1996). Modular neural networks evolved by genetic programming. 681-684. Paper presented at Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96, Nagoya, Jpn, .
Cho, Sung Bae ; Shimohara, Katsunori. / Modular neural networks evolved by genetic programming. Paper presented at Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96, Nagoya, Jpn, .4 p.
@conference{9e18826ced634e758e0cae690fbf406a,
title = "Modular neural networks evolved by genetic programming",
abstract = "In this paper we present an evolvable model of modular neural networks which are rich in autonomy and creativity. In order to build an artificial neural network which is rich in autonomy and creativity, we have adopted the ideas and methodologies of Artificial Life. This paper describes the concepts and methodologies for the evolvable model of modular neural networks, which will be able not only to develop new functionality spontaneously but also to grow and evolve its own structure autonomously. Although the ultimate goal of this model is to design the control system for such behavior-based robots as Khepera, we have attempted to apply the mechanism to a visual categorization task with handwritten digits. The evolutionary mechanism has shown a strong possibility to generate useful network architectures from an initial set of randomly-connected networks.",
author = "Cho, {Sung Bae} and Katsunori Shimohara",
year = "1996",
month = "1",
day = "1",
language = "English",
pages = "681--684",
note = "Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96 ; Conference date: 20-05-1996 Through 22-05-1996",

}

Cho, SB & Shimohara, K 1996, 'Modular neural networks evolved by genetic programming' Paper presented at Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96, Nagoya, Jpn, 96/5/20 - 96/5/22, pp. 681-684.

Modular neural networks evolved by genetic programming. / Cho, Sung Bae; Shimohara, Katsunori.

1996. 681-684 Paper presented at Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96, Nagoya, Jpn, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Modular neural networks evolved by genetic programming

AU - Cho, Sung Bae

AU - Shimohara, Katsunori

PY - 1996/1/1

Y1 - 1996/1/1

N2 - In this paper we present an evolvable model of modular neural networks which are rich in autonomy and creativity. In order to build an artificial neural network which is rich in autonomy and creativity, we have adopted the ideas and methodologies of Artificial Life. This paper describes the concepts and methodologies for the evolvable model of modular neural networks, which will be able not only to develop new functionality spontaneously but also to grow and evolve its own structure autonomously. Although the ultimate goal of this model is to design the control system for such behavior-based robots as Khepera, we have attempted to apply the mechanism to a visual categorization task with handwritten digits. The evolutionary mechanism has shown a strong possibility to generate useful network architectures from an initial set of randomly-connected networks.

AB - In this paper we present an evolvable model of modular neural networks which are rich in autonomy and creativity. In order to build an artificial neural network which is rich in autonomy and creativity, we have adopted the ideas and methodologies of Artificial Life. This paper describes the concepts and methodologies for the evolvable model of modular neural networks, which will be able not only to develop new functionality spontaneously but also to grow and evolve its own structure autonomously. Although the ultimate goal of this model is to design the control system for such behavior-based robots as Khepera, we have attempted to apply the mechanism to a visual categorization task with handwritten digits. The evolutionary mechanism has shown a strong possibility to generate useful network architectures from an initial set of randomly-connected networks.

UR - http://www.scopus.com/inward/record.url?scp=0029702796&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029702796&partnerID=8YFLogxK

M3 - Paper

SP - 681

EP - 684

ER -

Cho SB, Shimohara K. Modular neural networks evolved by genetic programming. 1996. Paper presented at Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96, Nagoya, Jpn, .