Parallel distributed gradient descent and ascent methods

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

Abstract

Summary form only given, as follows. A new parallel distributed processing architecture called an entropy machine (EM) is proposed. This machine, which is based on an artificial neural network composed of massive neurons and interconnections, is used for solving a variety of NP-complete optimization problems. The EM performs either the parallel distributed gradient descent method or gradient ascent method to search for minima or maxima.

Original languageEnglish
Title of host publicationIJCNN Int Jt Conf Neural Network
Editors Anon
PublisherPubl by IEEE
Pages584
Number of pages1
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

Entropy
Neurons
Neural networks
Processing

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Takefuji, Y. (1989). Parallel distributed gradient descent and ascent methods. In Anon (Ed.), IJCNN Int Jt Conf Neural Network (pp. 584). Publ by IEEE.

Parallel distributed gradient descent and ascent methods. / Takefuji, Yoshiyasu.

IJCNN Int Jt Conf Neural Network. ed. / Anon. Publ by IEEE, 1989. p. 584.

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

Takefuji, Y 1989, Parallel distributed gradient descent and ascent methods. in Anon (ed.), IJCNN Int Jt Conf Neural Network. Publ by IEEE, pp. 584, IJCNN International Joint Conference on Neural Networks, Washington, DC, USA, 89/6/18.
Takefuji Y. Parallel distributed gradient descent and ascent methods. In Anon, editor, IJCNN Int Jt Conf Neural Network. Publ by IEEE. 1989. p. 584
Takefuji, Yoshiyasu. / Parallel distributed gradient descent and ascent methods. IJCNN Int Jt Conf Neural Network. editor / Anon. Publ by IEEE, 1989. pp. 584
@inproceedings{db40a6b0e977438081b600b1dea37108,
title = "Parallel distributed gradient descent and ascent methods",
abstract = "Summary form only given, as follows. A new parallel distributed processing architecture called an entropy machine (EM) is proposed. This machine, which is based on an artificial neural network composed of massive neurons and interconnections, is used for solving a variety of NP-complete optimization problems. The EM performs either the parallel distributed gradient descent method or gradient ascent method to search for minima or maxima.",
author = "Yoshiyasu Takefuji",
year = "1989",
language = "English",
pages = "584",
editor = "Anon",
booktitle = "IJCNN Int Jt Conf Neural Network",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Parallel distributed gradient descent and ascent methods

AU - Takefuji, Yoshiyasu

PY - 1989

Y1 - 1989

N2 - Summary form only given, as follows. A new parallel distributed processing architecture called an entropy machine (EM) is proposed. This machine, which is based on an artificial neural network composed of massive neurons and interconnections, is used for solving a variety of NP-complete optimization problems. The EM performs either the parallel distributed gradient descent method or gradient ascent method to search for minima or maxima.

AB - Summary form only given, as follows. A new parallel distributed processing architecture called an entropy machine (EM) is proposed. This machine, which is based on an artificial neural network composed of massive neurons and interconnections, is used for solving a variety of NP-complete optimization problems. The EM performs either the parallel distributed gradient descent method or gradient ascent method to search for minima or maxima.

UR - http://www.scopus.com/inward/record.url?scp=0024903299&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024903299&partnerID=8YFLogxK

M3 - Conference contribution

SP - 584

BT - IJCNN Int Jt Conf Neural Network

A2 - Anon, null

PB - Publ by IEEE

ER -