Neurons with an immunological rejective function and their application to scheduling problems

Ikuo Arizono, Shinji Hara, Hiroshi Ohta

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

1 Citation (Scopus)

Abstract

If the energy function of an artificial neural network system is expressed in quadratic form based on the objective function and constraints of a combinatorial optimization problem, it is possible to get a solution using the equations of system dynamics; a special algorithm is not required. However, even though the subenergy functions based on the constraints can be expressed in quadratic form, minimizing the subenergy functions does not necessarily give a feasible solution satisfying the constraints of the optimization problem. This shows that neural network systems have a limit in their applicability. In this paper we propose new neurons, with an immunological rejective function, so as to extend the applicability of neural network system. These neurons have the function of rejecting the violation of constraints. We apply these neurons to scheduling problems and discuss their capabilities.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Editors Anon
PublisherPubl by IEEE
Pages1520-1523
Number of pages4
Volume2
ISBN (Print)0780314212
Publication statusPublished - 1993
Externally publishedYes
EventProceedings of 1993 International Joint Conference on Neural Networks. Part 2 (of 3) - Nagoya, Jpn
Duration: Oct 25 1993Oct 29 1993

Other

OtherProceedings of 1993 International Joint Conference on Neural Networks. Part 2 (of 3)
CityNagoya, Jpn
Period10/25/9310/29/93

Fingerprint

Neurons
Scheduling
Neural networks
Combinatorial optimization
Dynamical systems

ASJC Scopus subject areas

  • Software

Cite this

Arizono, I., Hara, S., & Ohta, H. (1993). Neurons with an immunological rejective function and their application to scheduling problems. In Anon (Ed.), Proceedings of the International Joint Conference on Neural Networks (Vol. 2, pp. 1520-1523). Publ by IEEE.

Neurons with an immunological rejective function and their application to scheduling problems. / Arizono, Ikuo; Hara, Shinji; Ohta, Hiroshi.

Proceedings of the International Joint Conference on Neural Networks. ed. / Anon. Vol. 2 Publ by IEEE, 1993. p. 1520-1523.

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

Arizono, I, Hara, S & Ohta, H 1993, Neurons with an immunological rejective function and their application to scheduling problems. in Anon (ed.), Proceedings of the International Joint Conference on Neural Networks. vol. 2, Publ by IEEE, pp. 1520-1523, Proceedings of 1993 International Joint Conference on Neural Networks. Part 2 (of 3), Nagoya, Jpn, 10/25/93.
Arizono I, Hara S, Ohta H. Neurons with an immunological rejective function and their application to scheduling problems. In Anon, editor, Proceedings of the International Joint Conference on Neural Networks. Vol. 2. Publ by IEEE. 1993. p. 1520-1523
Arizono, Ikuo ; Hara, Shinji ; Ohta, Hiroshi. / Neurons with an immunological rejective function and their application to scheduling problems. Proceedings of the International Joint Conference on Neural Networks. editor / Anon. Vol. 2 Publ by IEEE, 1993. pp. 1520-1523
@inproceedings{5e28aa0c981a49a5867dedee8a862336,
title = "Neurons with an immunological rejective function and their application to scheduling problems",
abstract = "If the energy function of an artificial neural network system is expressed in quadratic form based on the objective function and constraints of a combinatorial optimization problem, it is possible to get a solution using the equations of system dynamics; a special algorithm is not required. However, even though the subenergy functions based on the constraints can be expressed in quadratic form, minimizing the subenergy functions does not necessarily give a feasible solution satisfying the constraints of the optimization problem. This shows that neural network systems have a limit in their applicability. In this paper we propose new neurons, with an immunological rejective function, so as to extend the applicability of neural network system. These neurons have the function of rejecting the violation of constraints. We apply these neurons to scheduling problems and discuss their capabilities.",
author = "Ikuo Arizono and Shinji Hara and Hiroshi Ohta",
year = "1993",
language = "English",
isbn = "0780314212",
volume = "2",
pages = "1520--1523",
editor = "Anon",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Neurons with an immunological rejective function and their application to scheduling problems

AU - Arizono, Ikuo

AU - Hara, Shinji

AU - Ohta, Hiroshi

PY - 1993

Y1 - 1993

N2 - If the energy function of an artificial neural network system is expressed in quadratic form based on the objective function and constraints of a combinatorial optimization problem, it is possible to get a solution using the equations of system dynamics; a special algorithm is not required. However, even though the subenergy functions based on the constraints can be expressed in quadratic form, minimizing the subenergy functions does not necessarily give a feasible solution satisfying the constraints of the optimization problem. This shows that neural network systems have a limit in their applicability. In this paper we propose new neurons, with an immunological rejective function, so as to extend the applicability of neural network system. These neurons have the function of rejecting the violation of constraints. We apply these neurons to scheduling problems and discuss their capabilities.

AB - If the energy function of an artificial neural network system is expressed in quadratic form based on the objective function and constraints of a combinatorial optimization problem, it is possible to get a solution using the equations of system dynamics; a special algorithm is not required. However, even though the subenergy functions based on the constraints can be expressed in quadratic form, minimizing the subenergy functions does not necessarily give a feasible solution satisfying the constraints of the optimization problem. This shows that neural network systems have a limit in their applicability. In this paper we propose new neurons, with an immunological rejective function, so as to extend the applicability of neural network system. These neurons have the function of rejecting the violation of constraints. We apply these neurons to scheduling problems and discuss their capabilities.

UR - http://www.scopus.com/inward/record.url?scp=0027814459&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027814459&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027814459

SN - 0780314212

VL - 2

SP - 1520

EP - 1523

BT - Proceedings of the International Joint Conference on Neural Networks

A2 - Anon, null

PB - Publ by IEEE

ER -