New genetic approach to universal rule generation from trained neural networks

Minoru Fukumi, Yasue Mitsukura, Norio Akamatsu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper a new rule generation method from neural networks is presented. A neural network (NN) is formed using a genetic algorithm (GA) with virus infection and deterministic mutation to represent regularities in training data. This method utilizes a modular structure in GA. Each module learns a different neural network architecture, such as sigmoid and a higher order neural networks. Those chromosome information is communicated to the other modules by the virus infection. The higher order units are connected to an output unit or hidden units. By using these architectures, rules can be extracted. The results of computer simulations show that this approach can generate obvious, network architectures and as a result simple rules.

Original languageEnglish
Title of host publicationIEEE Region 10 Annual International Conference, Proceedings/TENCON
Volume1
Publication statusPublished - 2000
Externally publishedYes
Event2000 TENCON Proceedings - Kuala Lumpur, Malaysia
Duration: 2000 Sep 242000 Sep 27

Other

Other2000 TENCON Proceedings
CityKuala Lumpur, Malaysia
Period00/9/2400/9/27

Fingerprint

Neural networks
Network architecture
Viruses
Genetic algorithms
Chromosomes
Computer simulation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Fukumi, M., Mitsukura, Y., & Akamatsu, N. (2000). New genetic approach to universal rule generation from trained neural networks. In IEEE Region 10 Annual International Conference, Proceedings/TENCON (Vol. 1)

New genetic approach to universal rule generation from trained neural networks. / Fukumi, Minoru; Mitsukura, Yasue; Akamatsu, Norio.

IEEE Region 10 Annual International Conference, Proceedings/TENCON. Vol. 1 2000.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Fukumi, M, Mitsukura, Y & Akamatsu, N 2000, New genetic approach to universal rule generation from trained neural networks. in IEEE Region 10 Annual International Conference, Proceedings/TENCON. vol. 1, 2000 TENCON Proceedings, Kuala Lumpur, Malaysia, 00/9/24.
Fukumi M, Mitsukura Y, Akamatsu N. New genetic approach to universal rule generation from trained neural networks. In IEEE Region 10 Annual International Conference, Proceedings/TENCON. Vol. 1. 2000
Fukumi, Minoru ; Mitsukura, Yasue ; Akamatsu, Norio. / New genetic approach to universal rule generation from trained neural networks. IEEE Region 10 Annual International Conference, Proceedings/TENCON. Vol. 1 2000.
@inproceedings{387af34126ad46dba8109e7ae9748378,
title = "New genetic approach to universal rule generation from trained neural networks",
abstract = "In this paper a new rule generation method from neural networks is presented. A neural network (NN) is formed using a genetic algorithm (GA) with virus infection and deterministic mutation to represent regularities in training data. This method utilizes a modular structure in GA. Each module learns a different neural network architecture, such as sigmoid and a higher order neural networks. Those chromosome information is communicated to the other modules by the virus infection. The higher order units are connected to an output unit or hidden units. By using these architectures, rules can be extracted. The results of computer simulations show that this approach can generate obvious, network architectures and as a result simple rules.",
author = "Minoru Fukumi and Yasue Mitsukura and Norio Akamatsu",
year = "2000",
language = "English",
volume = "1",
booktitle = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",

}

TY - GEN

T1 - New genetic approach to universal rule generation from trained neural networks

AU - Fukumi, Minoru

AU - Mitsukura, Yasue

AU - Akamatsu, Norio

PY - 2000

Y1 - 2000

N2 - In this paper a new rule generation method from neural networks is presented. A neural network (NN) is formed using a genetic algorithm (GA) with virus infection and deterministic mutation to represent regularities in training data. This method utilizes a modular structure in GA. Each module learns a different neural network architecture, such as sigmoid and a higher order neural networks. Those chromosome information is communicated to the other modules by the virus infection. The higher order units are connected to an output unit or hidden units. By using these architectures, rules can be extracted. The results of computer simulations show that this approach can generate obvious, network architectures and as a result simple rules.

AB - In this paper a new rule generation method from neural networks is presented. A neural network (NN) is formed using a genetic algorithm (GA) with virus infection and deterministic mutation to represent regularities in training data. This method utilizes a modular structure in GA. Each module learns a different neural network architecture, such as sigmoid and a higher order neural networks. Those chromosome information is communicated to the other modules by the virus infection. The higher order units are connected to an output unit or hidden units. By using these architectures, rules can be extracted. The results of computer simulations show that this approach can generate obvious, network architectures and as a result simple rules.

UR - http://www.scopus.com/inward/record.url?scp=0034429306&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034429306&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0034429306

VL - 1

BT - IEEE Region 10 Annual International Conference, Proceedings/TENCON

ER -