Spiking Neural Network Adapted to the Shortest Path Problem
DOI:
https://doi.org/10.30973/progmat/2019.11.2/1Keywords:
Spiking Neural Network, Optimization, Shortest Path Problem, Knowledge Explicitation, Parallel DesignAbstract
The efficient solution of the shortest path problem has applications in such important and current areas as robotics, telecommunications, operations research, game theory, computer networks, internet, industrial design, transport phenomena, design of electronic circuits and others, so it is a subject of great interest in the area of combinatorial optimization. In the present work, we describe a Spiking Artificial Neural Network capable of efficiently attack the problem of the shortest path between two nodes. Once the Spiking Network finds the target node at minimum cost, an extraction or Knowledge Explicitation of this Network is performed to recover the final trajectory. Due to the parallel design of the Neural Network presented here, this solution approach can be highly competitive, as observed from the good results obtained in the experimental phase, even in cases with thousands of nodes.
References
Moustapha, D., Mark, K., Advances in combinatorial optimization, World Scientific, 2016.
Thulasiraman, K., Arumugam, S., et al., Handbook of graph theory, CRC Press, 2016.
Beck, A., First-Order Methods in Optimization, Vol 25 de MOS-SIAM Series on optimization, 2017.
Daniel, G., Principles of artificial neural networks, World Scientific, 2013.
Lindblad, T., Kinser, J., Image processing using pulse-coupled neural networks, Springer, 1998.
Chuanli, Z., Jinzheng, R., Elicitation of decision maker preference by artificial neural networks, IEEE Int.Conf. on Neural networks and brain, 2005. https://doi.org/10.1109/ICNNB.2005.1614956
Ma, Y., Zhan, K., Wang, Z., Applications of pulse–coupled neural networks, Springer, 2011.
Kirk, D., GPU Gems, Addison-Wesley, 2004.
Computer science. Recuperado en abril 2018, de https://cs.stackexchange.com/questions/1151/whereto-get-graphs-to-test-my-search-algorithms-against.
Brinkhoff, T., Recuperado en abril 2018, de https://www.cs.utah.edu/~lifeifei/SpatialDataset.htm .
Syed, U.A., Kunwar, F., Iqbal, M., Guided autowave pulse coupled neural network (GAPCNN) based real time path planning and an obstacle avoidance scheme for mobile robots, Robotics and autonomous systems, 62, 2014, 474-486. https://doi.org/10.1016/j.robot.2013.12.004
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2019 Programación Matemática y Software
This work is licensed under a Creative Commons Attribution 4.0 International License.
Usted es libre de:
 |
Compartir — compartir y redistribuir el material publicado en cualquier medio o formato. |
 |
Adaptar — combinar, transformar y construir sobre el material para cualquier propósito, incluso comercialmente. |
Bajo las siguientes condiciones:
 |
Atribución — Debe otorgar el crédito correspondiente, proporcionar un enlace a la licencia e indicar si se realizaron cambios. Puede hacerlo de cualquier manera razonable, pero de ninguna manera que sugiera que el licenciador lo respalda a usted o a su uso. |
| Sin restricciones adicionales: no puede aplicar términos legales o medidas tecnológicas que restrinjan legalmente a otros a hacer cualquier cosa que permita la licencia. |
