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 |
|---|---|
| Pages (from-to) | 437 |
| Number of pages | 1 |
| Journal | Neural Networks |
| Volume | 1 |
| Issue number | 1 SUPPL |
| DOIs | |
| Publication status | Published - 1988 |
| Externally published | Yes |
Fingerprint
ASJC Scopus subject areas
- Artificial Intelligence
- Neuroscience(all)
Cite this
Binary neurons with analog communication links for solving large-scale optimization problems. / Foo, Yoon Pin Simon; Takefuji, Yoshiyasu; Szu, Harold.
In: Neural Networks, Vol. 1, No. 1 SUPPL, 1988, p. 437.Research output: Contribution to journal › Article
}
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
Y1 - 1988
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 - Article
AN - SCOPUS:0024173771
VL - 1
SP - 437
JO - Neural Networks
JF - Neural Networks
SN - 0893-6080
IS - 1 SUPPL
ER -