Limitations of neural networks for solving traveling salesman problems

@article{Gee1995LimitationsON,
  title={Limitations of neural networks for solving traveling salesman problems},
  author={Andrew H. Gee and Richard W. Prager},
  journal={IEEE transactions on neural networks},
  year={1995},
  volume={6 1},
  pages={280-2}
}
Feedback neural networks enjoy considerable popularity as a means of approximately solving combinatorial optimization problems. It is now well established how to map problems onto networks so that invalid solutions are never found. It is not as clear how the networks' solutions compare in terms of quality with those obtained using other optimization techniques; such issues are addressed in this paper. A linearized analysis of annealed network dynamics allows a prototypical network solution to… CONTINUE READING
Highly Cited
This paper has 36 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 4 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 22 extracted citations

Using passive neural networks to solve TSP

2015 IEEE 2nd International Conference on Cybernetics (CYBCONF) • 2015
View 1 Excerpt

Neural networks based on adjustable-order statistic filters for multimedia multicast routing

2014 Third IEEE International Colloquium in Information Science and Technology (CIST) • 2014
View 2 Excerpts

References

Publications referenced by this paper.
Showing 1-10 of 11 references

Graph partitioning using annealed neural networks

International 1989 Joint Conference on Neural Networks • 1989

Soderbeg, “A new method for mapping optimization problems onto neural networks,

B. C. Peterson
fnt. 1. Neural Sysr., • 1989

Applicability of mean field theory neural network methods to the graph partitioning problem

D. Ddud S. P. Eberhart, D. A. Kems, T. X. Brown, A. P. Thakoor
1988

Pawey. “On the stability of the TSP problem algorithm of Hopfield and Tank,

G.S.V. Wilson
Biological Cybernetics, • 1988

Neurons with graded response have collective computational properties like those of two-state neurons.

Proceedings of the National Academy of Sciences of the United States of America • 1984

Similar Papers

Loading similar papers…