Traveling Salesman Problem Solutions by Using Passive Neural Networks

Andrzej Luksza, Wieslaw Sienko

2014

Abstract

Presented in this paper numeric experiments on random, relative large travelling salesman problems, show that the passive neural networks can be used as an efficient, dynamic optimization tool for combinatorial programming. Moreover, the passive neural networks, when implemented in VLSI technology, could be a basis for structure of bio-inspired processors, for real-time optimizations.

References

  1. Warren, R. H.: Numeric Experiments on the Commercial Quantum Computer, Notices of the AMS, Vol. 60, No 11 (2013)
  2. Luksza, A.: Badanie Realizowalnosci Wielkich Sieci Neuronowych, Dissertation (in Polish), Gdansk University of Technology (1997)
  3. t'Hooft, G.: Determinism and Dissipation in Quantum Gravity, arXiv:hep-th/0003005 v 2,16 (2000)
  4. Hopfield, J. J., Tank, D. W.: Neural computation of decisions in optimization problems, Biological Cybernatics, vol.52 (1985)
  5. Sienko, W., Luksza, A., Citko, W.: On Properties of Passive Neural Networks, Wydawnictwa Uczelniane WSM, Gdynia (1993), ISSN - 0324 - 8887
  6. Abe, S., Gee, A. H.: Global Convergence of the Hopfield Neural Network with Nonzero Diagonal Elements, IEEE Tr. on CAS, vol.42, No 1 (1995)
  7. Gee, A. H., Prager, R.W.: Limitations of Neural Networks for Solving Traveling Salesman Problems, IEEE Tr. on Neural Networks, vol.6, No 1 (1995)
  8. Haykin, S.: Neural Networks and Learning Machines, Person Education, Inc., N.J. (2009)
Download


Paper Citation


in Harvard Style

Luksza A. and Sienko W. (2014). Traveling Salesman Problem Solutions by Using Passive Neural Networks . In Proceedings of the International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2014) ISBN 978-989-758-041-3, pages 69-77. DOI: 10.5220/0005132800690077


in Bibtex Style

@conference{anniip14,
author={Andrzej Luksza and Wieslaw Sienko},
title={Traveling Salesman Problem Solutions by Using Passive Neural Networks},
booktitle={Proceedings of the International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2014)},
year={2014},
pages={69-77},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005132800690077},
isbn={978-989-758-041-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Workshop on Artificial Neural Networks and Intelligent Information Processing - Volume 1: ANNIIP, (ICINCO 2014)
TI - Traveling Salesman Problem Solutions by Using Passive Neural Networks
SN - 978-989-758-041-3
AU - Luksza A.
AU - Sienko W.
PY - 2014
SP - 69
EP - 77
DO - 10.5220/0005132800690077