Design of parallel distributed Cauchy machines

Yoshiyasu Takefuji, Harold Szu

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

26 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationIJCNN Int Jt Conf Neural Network
Editors Anon
PublisherPubl by IEEE
Pages529-532
Number of pages4
Publication statusPublished - 1989
Externally publishedYes
EventIJCNN International Joint Conference on Neural Networks - Washington, DC, USA
Duration: 1989 Jun 181989 Jun 22

Other

OtherIJCNN International Joint Conference on Neural Networks
CityWashington, DC, USA
Period89/6/1889/6/22

Fingerprint

Cooling
Simulated annealing
Neurons
Color
Neural networks

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Takefuji, Y., & Szu, H. (1989). Design of parallel distributed Cauchy machines. In Anon (Ed.), IJCNN Int Jt Conf Neural Network (pp. 529-532). Publ by IEEE.

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

IJCNN Int Jt Conf Neural Network. ed. / Anon. Publ by IEEE, 1989. p. 529-532.

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

Takefuji, Y & Szu, H 1989, Design of parallel distributed Cauchy machines. in Anon (ed.), 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.
Takefuji Y, Szu H. Design of parallel distributed Cauchy machines. In Anon, editor, IJCNN Int Jt Conf Neural Network. Publ by IEEE. 1989. p. 529-532
Takefuji, Yoshiyasu ; Szu, Harold. / Design of parallel distributed Cauchy machines. IJCNN Int Jt Conf Neural Network. editor / Anon. Publ by IEEE, 1989. pp. 529-532
@inproceedings{131d39fed0944765af02b9706cdc56ed,
title = "Design of parallel distributed Cauchy machines",
abstract = "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.",
author = "Yoshiyasu Takefuji and Harold Szu",
year = "1989",
language = "English",
pages = "529--532",
editor = "Anon",
booktitle = "IJCNN Int Jt Conf Neural Network",
publisher = "Publ by IEEE",

}

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

SP - 529

EP - 532

BT - IJCNN Int Jt Conf Neural Network

A2 - Anon, null

PB - Publ by IEEE

ER -