An Effective Traveling Salesman Problem Solver Based on Self-Organizing Map

Authors:
Alessio Plebe
Affiliations:
-
Venue:
ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Year:
2002

Citing 7
Cited 0

“Conscientious” neural nets for tour construction in the traveling salesman problem: the vigilant net

Computers and Operations Research
The Kohonen network incorporating explicit statistics and its application to the travelling salesman problem

Neural Networks
Self-Organizing Maps

Self-Organizing Maps
A neural-network-based approach to the double traveling salesman problem

Neural Computation
Neural Networks for Combinatorial Optimization: a Review of More Than a Decade of Research

INFORMS Journal on Computing
Vision and Neural Control for an Orange Harvesting Robot

NICROSP '96 Proceedings of the 1996 International Workshop on Neural Networks for Identification, Control, Robotics, and Signal/Image Processing (NICROSP '96)
An argument for abandoning the travelling salesman problem as a neural-network benchmark

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Combinatorial optimization seems to be a harsh field for Artificial Neural Networks (ANN), and in particular the Traveling Salesman Problem (TSP) is an exemplar benchmark where ANN today are not competitive with the best heuristics from the operations research literature. The thesis upheld in this work is that the Self-Organizing feature Map (SOM) paradigm can be an effective solving method for the TSP, if combined with appropriate mechanisms improving the efficiency and the accuracy. An original TSP-solver based on the SOM is tested over the largest TSP benchmarks, on which other ANN typically fail.