### 抄録

A parallel and stochastic version of Hopfield-like neural networks is presented. Cauchy color noise is assumed. The specific noise is desirable for fast convergence to a fixed point representing a neighborhood minimum. It can be quickly quenched at each iteration according to a proven cooling schedule in generating random states on the energy landscape. An exact Cauchy acceptance criterion is analytically derived for hill-climbing capability. The improvement is twofold: a faster cooling schedule (the inversely linear cooling schedule characterized by the Cauchy simulated annealing) and parallel executions of all neurons. Such a Cauchy machine can be electronically implemented, and the design is given.

元の言語 | English |
---|---|

ホスト出版物のタイトル | IJCNN Int Jt Conf Neural Network |

編集者 | Anon |

出版者 | Publ by IEEE |

ページ | 529-532 |

ページ数 | 4 |

出版物ステータス | Published - 1989 |

外部発表 | Yes |

イベント | IJCNN International Joint Conference on Neural Networks - Washington, DC, USA 継続期間: 1989 6 18 → 1989 6 22 |

### Other

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

市 | Washington, DC, USA |

期間 | 89/6/18 → 89/6/22 |

### Fingerprint

### ASJC Scopus subject areas

- Engineering(all)

### これを引用

*IJCNN Int Jt Conf Neural Network*(pp. 529-532). Publ by IEEE.

**Design of parallel distributed Cauchy machines.** / Takefuji, Yoshiyasu; Szu, Harold.

研究成果: Conference contribution

*IJCNN Int Jt Conf Neural Network.*Publ by IEEE, pp. 529-532, IJCNN International Joint Conference on Neural Networks, Washington, DC, USA, 89/6/18.

}

TY - GEN

T1 - Design of parallel distributed Cauchy machines

AU - Takefuji, Yoshiyasu

AU - Szu, Harold

PY - 1989

Y1 - 1989

N2 - A parallel and stochastic version of Hopfield-like neural networks is presented. Cauchy color noise is assumed. The specific noise is desirable for fast convergence to a fixed point representing a neighborhood minimum. It can be quickly quenched at each iteration according to a proven cooling schedule in generating random states on the energy landscape. An exact Cauchy acceptance criterion is analytically derived for hill-climbing capability. The improvement is twofold: a faster cooling schedule (the inversely linear cooling schedule characterized by the Cauchy simulated annealing) and parallel executions of all neurons. Such a Cauchy machine can be electronically implemented, and the design is given.

AB - A parallel and stochastic version of Hopfield-like neural networks is presented. Cauchy color noise is assumed. The specific noise is desirable for fast convergence to a fixed point representing a neighborhood minimum. It can be quickly quenched at each iteration according to a proven cooling schedule in generating random states on the energy landscape. An exact Cauchy acceptance criterion is analytically derived for hill-climbing capability. The improvement is twofold: a faster cooling schedule (the inversely linear cooling schedule characterized by the Cauchy simulated annealing) and parallel executions of all neurons. Such a Cauchy machine can be electronically implemented, and the design is given.

UR - http://www.scopus.com/inward/record.url?scp=0024921358&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024921358&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0024921358

SP - 529

EP - 532

BT - IJCNN Int Jt Conf Neural Network

A2 - Anon, null

PB - Publ by IEEE

ER -