### Abstract

The max cut problem, one of the NP-complete problems, was chosen to test the capability of an artificial neural network. The algorithm based on the maximum neural network was tested by 1000 randomly generated examples, including up to 300 vertex problems. The simulation result shows that the proposed parallel algorithm using the maximum neural network generates better solutions than Hsu's algorithm within one hundred iteration steps, regardless of the problem size.

Original language | English |
---|---|

Title of host publication | Proceedings. IJCNN-91-Seattle: International Joint Conference on Neural Networks |

Editors | Anon |

Publisher | Publ by IEEE |

Pages | 379-384 |

Number of pages | 6 |

ISBN (Print) | 0780301641 |

Publication status | Published - 1991 |

Externally published | Yes |

Event | International Joint Conference on Neural Networks - IJCNN-91-Seattle - Seattle, WA, USA Duration: 1991 Jul 8 → 1991 Jul 12 |

### Other

Other | International Joint Conference on Neural Networks - IJCNN-91-Seattle |
---|---|

City | Seattle, WA, USA |

Period | 91/7/8 → 91/7/12 |

### Fingerprint

### ASJC Scopus subject areas

- Engineering(all)

### Cite this

*Proceedings. IJCNN-91-Seattle: International Joint Conference on Neural Networks*(pp. 379-384). Publ by IEEE.

**A maximum neural network for the max cut problem.** / Lee, Kuo Chun; Takefuji, Yoshiyasu; Funabiki, Nobuo.

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

*Proceedings. IJCNN-91-Seattle: International Joint Conference on Neural Networks.*Publ by IEEE, pp. 379-384, International Joint Conference on Neural Networks - IJCNN-91-Seattle, Seattle, WA, USA, 91/7/8.

}

TY - GEN

T1 - A maximum neural network for the max cut problem

AU - Lee, Kuo Chun

AU - Takefuji, Yoshiyasu

AU - Funabiki, Nobuo

PY - 1991

Y1 - 1991

N2 - The max cut problem, one of the NP-complete problems, was chosen to test the capability of an artificial neural network. The algorithm based on the maximum neural network was tested by 1000 randomly generated examples, including up to 300 vertex problems. The simulation result shows that the proposed parallel algorithm using the maximum neural network generates better solutions than Hsu's algorithm within one hundred iteration steps, regardless of the problem size.

AB - The max cut problem, one of the NP-complete problems, was chosen to test the capability of an artificial neural network. The algorithm based on the maximum neural network was tested by 1000 randomly generated examples, including up to 300 vertex problems. The simulation result shows that the proposed parallel algorithm using the maximum neural network generates better solutions than Hsu's algorithm within one hundred iteration steps, regardless of the problem size.

UR - http://www.scopus.com/inward/record.url?scp=0026400953&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026400953&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780301641

SP - 379

EP - 384

BT - Proceedings. IJCNN-91-Seattle: International Joint Conference on Neural Networks

A2 - Anon, null

PB - Publ by IEEE

ER -