SCALABILITY OF A NEURAL-NETWORK FOR THE KNIGHTS TOUR PROBLEM

Authors
PARBERRY I
Citation
I. Parberry, SCALABILITY OF A NEURAL-NETWORK FOR THE KNIGHTS TOUR PROBLEM, Neurocomputing, 12(1), 1996, pp. 19-33
Citations number
18
Categorie Soggetti
Computer Sciences, Special Topics","Computer Science Artificial Intelligence",Neurosciences
Journal title
Neurocomputing → ACNP
ISSN journal
09252312
Volume
12
Issue
1
Year of publication
1996
Pages
19 - 33
Database
ISI
SICI code
0925-2312(1996)12:1<19:SOANFT>2.0.ZU;2-A
Abstract
The effectiveness and efficiency of a Hopfield-style neural network re cently proposed by Takefuji and Lee for the knight's tour problem on a n nxn board are compared and contrasted with standard algorithmic tech niques using a combination of experimental and theoretical analysis. E xperiments indicate that the neural network has poor performance when implemented on a conventional computer, and it is further argued that it is unlikely to improve significantly when implemented in parallel.