Adapting the Energy Landscape for MFA.
Journal of Artificial Neural Networks
We combine Mean Field Annealing (MFA)  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 , MFA at a constant temperature and a stochastic weight penalty technique, known as GENET, proposed by Tsang & Wang (1992) 
|Title:||Adapting the Energy Landscape for MFA|
|Additional information:||Special issue on Neural Networks for Optimization|
|UCL classification:||UCL > School of BEAMS > Faculty of Engineering Science
UCL > School of BEAMS > Faculty of Engineering Science > Computer Science
Archive Staff Only