An evolutionary neural network algorithm for max cut problems

N. Funabiki; J. Kitamichi; S. Nishikawa

doi:10.1109/ICNN.1997.616215

An evolutionary neural network algorithm for max cut problems

N. Funabiki, J. Kitamichi, S. Nishikawa

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

7 Citations (Scopus)

Abstract

An «evolutionary neural network (ENN)» is presented for the max cut problem of an undirected graph G(V, E) in this paper. The goal of the NP-hard problem is to find a partition of V into two disjoint subsets such that the cut size be maximized. The cut size is the sum of weights on edges in E whose endpoints belong to different subsets. The ENN combines the evolutionary initialization scheme of the neural state into the energy minimization criteria of the binary neural network. The performance of ENN is evaluated through simulations in randomly weighted complete graphs and unweighted random graphs with up to 1000 vertices. The results show that the evolutionary initialization scheme drastically improves the solution quality. ENN can always find better solutions than the maximum neural network, the mean field annealing, the simulated annealing, and the greedy algorithm.

Original language	English
Title of host publication	1997 IEEE International Conference on Neural Networks, ICNN 1997
Pages	1260-1265
Number of pages	6
DOIs	https://doi.org/10.1109/ICNN.1997.616215
Publication status	Published - 1997
Externally published	Yes
Event	1997 IEEE International Conference on Neural Networks, ICNN 1997 - Houston, TX, United States Duration: Jun 9 1997 → Jun 12 1997

Publication series

Name	IEEE International Conference on Neural Networks - Conference Proceedings
Volume	2
ISSN (Print)	1098-7576

Conference

Conference	1997 IEEE International Conference on Neural Networks, ICNN 1997
Country	United States
City	Houston, TX
Period	6/9/97 → 6/12/97

ASJC Scopus subject areas

Software

Access to Document

10.1109/ICNN.1997.616215

Fingerprint Dive into the research topics of 'An evolutionary neural network algorithm for max cut problems'. Together they form a unique fingerprint.

Cite this

An evolutionary neural network algorithm for max cut problems. / Funabiki, N.; Kitamichi, J.; Nishikawa, S.

1997 IEEE International Conference on Neural Networks, ICNN 1997. 1997. p. 1260-1265 616215 (IEEE International Conference on Neural Networks - Conference Proceedings; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Funabiki, N, Kitamichi, J & Nishikawa, S 1997, An evolutionary neural network algorithm for max cut problems. in 1997 IEEE International Conference on Neural Networks, ICNN 1997., 616215, IEEE International Conference on Neural Networks - Conference Proceedings, vol. 2, pp. 1260-1265, 1997 IEEE International Conference on Neural Networks, ICNN 1997, Houston, TX, United States, 6/9/97. https://doi.org/10.1109/ICNN.1997.616215

@inproceedings{2e520bc419ee433a8877681183f45215,

title = "An evolutionary neural network algorithm for max cut problems",

abstract = "An «evolutionary neural network (ENN)» is presented for the max cut problem of an undirected graph G(V, E) in this paper. The goal of the NP-hard problem is to find a partition of V into two disjoint subsets such that the cut size be maximized. The cut size is the sum of weights on edges in E whose endpoints belong to different subsets. The ENN combines the evolutionary initialization scheme of the neural state into the energy minimization criteria of the binary neural network. The performance of ENN is evaluated through simulations in randomly weighted complete graphs and unweighted random graphs with up to 1000 vertices. The results show that the evolutionary initialization scheme drastically improves the solution quality. ENN can always find better solutions than the maximum neural network, the mean field annealing, the simulated annealing, and the greedy algorithm.",

author = "N. Funabiki and J. Kitamichi and S. Nishikawa",

year = "1997",

doi = "10.1109/ICNN.1997.616215",

language = "English",

isbn = "0780341228",

series = "IEEE International Conference on Neural Networks - Conference Proceedings",

pages = "1260--1265",

booktitle = "1997 IEEE International Conference on Neural Networks, ICNN 1997",

note = "1997 IEEE International Conference on Neural Networks, ICNN 1997 ; Conference date: 09-06-1997 Through 12-06-1997",

}

TY - GEN

T1 - An evolutionary neural network algorithm for max cut problems

AU - Funabiki, N.

AU - Kitamichi, J.

AU - Nishikawa, S.

PY - 1997

Y1 - 1997

N2 - An «evolutionary neural network (ENN)» is presented for the max cut problem of an undirected graph G(V, E) in this paper. The goal of the NP-hard problem is to find a partition of V into two disjoint subsets such that the cut size be maximized. The cut size is the sum of weights on edges in E whose endpoints belong to different subsets. The ENN combines the evolutionary initialization scheme of the neural state into the energy minimization criteria of the binary neural network. The performance of ENN is evaluated through simulations in randomly weighted complete graphs and unweighted random graphs with up to 1000 vertices. The results show that the evolutionary initialization scheme drastically improves the solution quality. ENN can always find better solutions than the maximum neural network, the mean field annealing, the simulated annealing, and the greedy algorithm.

AB - An «evolutionary neural network (ENN)» is presented for the max cut problem of an undirected graph G(V, E) in this paper. The goal of the NP-hard problem is to find a partition of V into two disjoint subsets such that the cut size be maximized. The cut size is the sum of weights on edges in E whose endpoints belong to different subsets. The ENN combines the evolutionary initialization scheme of the neural state into the energy minimization criteria of the binary neural network. The performance of ENN is evaluated through simulations in randomly weighted complete graphs and unweighted random graphs with up to 1000 vertices. The results show that the evolutionary initialization scheme drastically improves the solution quality. ENN can always find better solutions than the maximum neural network, the mean field annealing, the simulated annealing, and the greedy algorithm.

UR - http://www.scopus.com/inward/record.url?scp=0030660005&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030660005&partnerID=8YFLogxK

U2 - 10.1109/ICNN.1997.616215

DO - 10.1109/ICNN.1997.616215

M3 - Conference contribution

AN - SCOPUS:0030660005

SN - 0780341228

SN - 9780780341227

T3 - IEEE International Conference on Neural Networks - Conference Proceedings

SP - 1260

EP - 1265

BT - 1997 IEEE International Conference on Neural Networks, ICNN 1997

T2 - 1997 IEEE International Conference on Neural Networks, ICNN 1997

Y2 - 9 June 1997 through 12 June 1997

ER -