An argument for abandoning the travelling salesman problem as a neural-network benchmark

In this paper, a distinction is drawn between research which assesses the suitability of the Hopfield network for solving the travelling salesman problem (TSP) and research which attempts to determine the effectiveness of the Hopfield network as an optimization technique. It is argued that the TSP i...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on neural networks Vol. 7; no. 6; pp. 1542 - 1544
Main Author: Smith, K.
Format: Journal Article
Language:English
Published: New York, NY IEEE 01.11.1996
Institute of Electrical and Electronics Engineers
Subjects:
Applied sciences
Artificial intelligence
Australia
Computer networks
Computer science; control theory; systems
Connectionism. Neural networks
Exact sciences and technology
Hopfield neural networks
Integer linear programming
Neural networks
Operations research
Testing
Traveling salesman problems
Travelling salesman problem
Neural network
Hopfield model
Optimization
ISSN:1045-9227
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, a distinction is drawn between research which assesses the suitability of the Hopfield network for solving the travelling salesman problem (TSP) and research which attempts to determine the effectiveness of the Hopfield network as an optimization technique. It is argued that the TSP is generally misused as a benchmark for the latter goal, with the existence of an alternative linear formulation giving rise to unreasonable comparisons.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ISSN:1045-9227
DOI:10.1109/72.548187