Binary neurons with analog communication links for solving large-scale optimization problems

Yoon Pin Simon Foo; Yoshiyasu Takefuji; Harold Szu

doi:10.1016/0893-6080(88)90461-3

Binary neurons with analog communication links for solving large-scale optimization problems

Yoon Pin Simon Foo, Yoshiyasu Takefuji, Harold Szu

Research output: Contribution to journal › Conference article

5 Citations (Scopus)

Abstract

We explore the applications of binary neurons with analog conductance or communication links in solving large-scale NP-complete optimization problems such as the classical traveling salesperson problems (TSP) and job-shop scheduling. In particular, the energy function of J.J. Hopfield and D.W. Tank neural network model is reformulated so that the network is likely to converge to a proportional number of valid solutions as the size of problem scales up. G.V. Wilson and G.S. Pawley identified the reasons for failure on the Hopfield and Tank computation algorithm in their attempts to solve a 10-city TSP. K. Sheff and H. Szu proposed a necessary and sufficient condition based on binary neurons and traceless energy for a Hopfield and Tank network to converge to stable states. In this paper, we study the effectiveness of this fast neural network convergent scheme through two case studies: an n-job m-machine job-shop problem and an N-city TSP.

Original language	English
Number of pages	1
Journal	Neural Networks
Volume	1
Issue number	1 SUPPL
DOIs	https://doi.org/10.1016/0893-6080(88)90461-3
Publication status	Published - 1988 Jan 1
Externally published	Yes
Event	International Neural Network Society 1988 First Annual Meeting - Boston, MA, USA Duration: 1988 Sep 6 → 1988 Sep 10

ASJC Scopus subject areas

Cognitive Neuroscience
Artificial Intelligence

Access to Document

10.1016/0893-6080(88)90461-3

Fingerprint Dive into the research topics of 'Binary neurons with analog communication links for solving large-scale optimization problems'. Together they form a unique fingerprint.

Cite this

Foo, Y. P. S., Takefuji, Y., & Szu, H. (1988). Binary neurons with analog communication links for solving large-scale optimization problems. Neural Networks, 1(1 SUPPL). https://doi.org/10.1016/0893-6080(88)90461-3

@article{3e31353550e3439794edeaf1ef97a145,

title = "Binary neurons with analog communication links for solving large-scale optimization problems",

abstract = "We explore the applications of binary neurons with analog conductance or communication links in solving large-scale NP-complete optimization problems such as the classical traveling salesperson problems (TSP) and job-shop scheduling. In particular, the energy function of J.J. Hopfield and D.W. Tank neural network model is reformulated so that the network is likely to converge to a proportional number of valid solutions as the size of problem scales up. G.V. Wilson and G.S. Pawley identified the reasons for failure on the Hopfield and Tank computation algorithm in their attempts to solve a 10-city TSP. K. Sheff and H. Szu proposed a necessary and sufficient condition based on binary neurons and traceless energy for a Hopfield and Tank network to converge to stable states. In this paper, we study the effectiveness of this fast neural network convergent scheme through two case studies: an n-job m-machine job-shop problem and an N-city TSP.",

author = "Foo, {Yoon Pin Simon} and Yoshiyasu Takefuji and Harold Szu",

year = "1988",

month = jan,

day = "1",

doi = "10.1016/0893-6080(88)90461-3",

language = "English",

volume = "1",

journal = "Neural Networks",

issn = "0893-6080",

publisher = "Elsevier Limited",

number = "1 SUPPL",

note = "International Neural Network Society 1988 First Annual Meeting ; Conference date: 06-09-1988 Through 10-09-1988",

}

TY - JOUR

T1 - Binary neurons with analog communication links for solving large-scale optimization problems

AU - Foo, Yoon Pin Simon

AU - Takefuji, Yoshiyasu

AU - Szu, Harold

PY - 1988/1/1

Y1 - 1988/1/1

N2 - We explore the applications of binary neurons with analog conductance or communication links in solving large-scale NP-complete optimization problems such as the classical traveling salesperson problems (TSP) and job-shop scheduling. In particular, the energy function of J.J. Hopfield and D.W. Tank neural network model is reformulated so that the network is likely to converge to a proportional number of valid solutions as the size of problem scales up. G.V. Wilson and G.S. Pawley identified the reasons for failure on the Hopfield and Tank computation algorithm in their attempts to solve a 10-city TSP. K. Sheff and H. Szu proposed a necessary and sufficient condition based on binary neurons and traceless energy for a Hopfield and Tank network to converge to stable states. In this paper, we study the effectiveness of this fast neural network convergent scheme through two case studies: an n-job m-machine job-shop problem and an N-city TSP.

AB - We explore the applications of binary neurons with analog conductance or communication links in solving large-scale NP-complete optimization problems such as the classical traveling salesperson problems (TSP) and job-shop scheduling. In particular, the energy function of J.J. Hopfield and D.W. Tank neural network model is reformulated so that the network is likely to converge to a proportional number of valid solutions as the size of problem scales up. G.V. Wilson and G.S. Pawley identified the reasons for failure on the Hopfield and Tank computation algorithm in their attempts to solve a 10-city TSP. K. Sheff and H. Szu proposed a necessary and sufficient condition based on binary neurons and traceless energy for a Hopfield and Tank network to converge to stable states. In this paper, we study the effectiveness of this fast neural network convergent scheme through two case studies: an n-job m-machine job-shop problem and an N-city TSP.

UR - http://www.scopus.com/inward/record.url?scp=0024173771&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024173771&partnerID=8YFLogxK

U2 - 10.1016/0893-6080(88)90461-3

DO - 10.1016/0893-6080(88)90461-3

M3 - Conference article

AN - SCOPUS:0024173771

VL - 1

JO - Neural Networks

JF - Neural Networks

SN - 0893-6080

IS - 1 SUPPL

T2 - International Neural Network Society 1988 First Annual Meeting

Y2 - 6 September 1988 through 10 September 1988

ER -