NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Simulation tests of the optimization method of Hopfield and Tank using neural networksThe method proposed by Hopfield and Tank for using the Hopfield neural network with continuous valued neurons to solve the traveling salesman problem is tested by simulation. Several researchers have apparently been unable to successfully repeat the numerical simulation documented by Hopfield and Tank. However, as suggested to the author by Adams, it appears that the reason for those difficulties is that a key parameter value is reported erroneously (by four orders of magnitude) in the original paper. When a reasonable value is used for that parameter, the network performs generally as claimed. Additionally, a new method of using feedback to control the input bias currents to the amplifiers is proposed and successfully tested. This eliminates the need to set the input currents by trial and error.
Document ID
19890004633
Acquisition Source
Legacy CDMS
Document Type
Technical Memorandum (TM)
Authors
Paielli, Russell A.
(NASA Ames Research Center Moffett Field, CA, United States)
Date Acquired
September 5, 2013
Publication Date
November 1, 1988
Subject Category
Cybernetics
Report/Patent Number
A-88275
NAS 1.15:101047
NASA-TM-101047
Accession Number
89N14004
Funding Number(s)
PROJECT: RTOP 505-66-51
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.
No Preview Available