Adapting the Energy Landscape for MFA
Adapting the Energy Landscape for MFA
We combine Mean Field Annealing (MFA) [7] with an anti-hebbian type adaptive weight penalty method forming an algorithm that performs well on standard benchmark optimization problems. We compare the hybrid algorithm with the Petford and Welsh algorithm [5], MFA at a constant temperature[7] and a stochastic weight penalty technique, known as GENET, proposed by Tsang & Wang (1992) [8].
449-454
Burge, P.
b6e48fae-9a70-48ce-b27c-9502efb4e4a4
Shawe-Taylor, J.
c32d0ee4-b422-491f-8c28-78663851d6db
November 1995
Burge, P.
b6e48fae-9a70-48ce-b27c-9502efb4e4a4
Shawe-Taylor, J.
c32d0ee4-b422-491f-8c28-78663851d6db
Burge, P. and Shawe-Taylor, J.
(1995)
Adapting the Energy Landscape for MFA.
Journal of Artificial Neural Networks, 2 (4), .
Abstract
We combine Mean Field Annealing (MFA) [7] with an anti-hebbian type adaptive weight penalty method forming an algorithm that performs well on standard benchmark optimization problems. We compare the hybrid algorithm with the Petford and Welsh algorithm [5], MFA at a constant temperature[7] and a stochastic weight penalty technique, known as GENET, proposed by Tsang & Wang (1992) [8].
Text
Adapting_the_Energy_Landscape_for_MFA.pdf
- Other
More information
Published date: November 1995
Additional Information:
Special issue on Neural Networks for Optimization
Organisations:
Electronics & Computer Science
Identifiers
Local EPrints ID: 259805
URI: http://eprints.soton.ac.uk/id/eprint/259805
PURE UUID: b4e936c5-79ea-4bb0-b528-24dff1cac626
Catalogue record
Date deposited: 23 Aug 2004
Last modified: 14 Mar 2024 06:28
Export record
Contributors
Author:
P. Burge
Author:
J. Shawe-Taylor
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics