## Abstract

Two improved neural algorithms are presented for solving a placement problem which is a familiar class of NP-hard quadratic assignment problems. Formulation of the problem as a zero-one integer programming leads to an improved form of the Hopfield networks, while a mixed integer programming formulation results in an analogue algorithm similar to the elastic nets. The outermost loop in these algorithms performs an automatically scheduled deterministic annealing. This gives us a natural interpretation of the annealing procedure derived straightforwardly from the mathematical programming framework. Experiments reveal that the adaptive elastic net algorithm outperforms the adaptive Hopfield method.

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

Title of host publication | Proceedings of the International Joint Conference on Neural Networks |

Publisher | Publ by IEEE |

Pages | 2421-2424 |

Number of pages | 4 |

Volume | 3 |

ISBN (Print) | 0780314212, 9780780314214 |

Publication status | Published - 1993 |

Externally published | Yes |

Event | Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn Duration: Oct 25 1993 → Oct 29 1993 |

### Other

Other | Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) |
---|---|

City | Nagoya, Jpn |

Period | 10/25/93 → 10/29/93 |

## All Science Journal Classification (ASJC) codes

- Engineering(all)