Adapting the Energy Landscape for MFA

Burge, P. and Shawe-Taylor, J. (1995) Adapting the Energy Landscape for MFA. Journal of Artificial Neural Networks, 2, (4), 449-454.


[img] PDF
Download (132Kb)


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].

Item Type: Article
Additional Information: Special issue on Neural Networks for Optimization
Divisions : Faculty of Physical Sciences and Engineering > Electronics and Computer Science
ePrint ID: 259805
Accepted Date and Publication Date:
November 1995Published
Date Deposited: 23 Aug 2004
Last Modified: 31 Mar 2016 14:01
Further Information:Google Scholar

Actions (login required)

View Item View Item