A hybrid neural optimization scheme based on parallel updates

see the original item page
in the repository's web site and access all digital files if the item*

1998 (EN)
A hybrid neural optimization scheme based on parallel updates (EN)

Papageorgiou, G (EN)
Likas, A (EN)
Stafylopatis, A (EN)

N/A (EN)

A synchronous Hopfield-type neural network model containing units with analog input and binary output. which is suitable for parallel implementation, is examined in the context of solving discrete optimization, problems. A hybrid parallel update scheme concerning the stochastic input-output behaviour of each unit is presented. This parallel update scheme maintains the solution quality of the Boltzmann Machine optimizer, which is inherently sequential. Experimental results on the Maximum Independent Set problem demonstrate the benefit of using the proposed optimizer in terms of computation time. Excellent speedup has been obtained through parallel implementation on both shared memory and distributed memory architecures. (EN)


Data storage equipment (EN)
Computational complexity (EN)
Optimization (EN)
Parallel processing systems (EN)
Boltzmann machine optimizer (EN)
Parallel computing (EN)
Cauchy Machine (EN)
Neural networks (EN)
Computer architecture (EN)
Problem solving (EN)
Hopfield type neural network models (EN)
Mathematical models (EN)
Boltzmann Machine (EN)

Εθνικό Μετσόβιο Πολυτεχνείο (EL)
National Technical University of Athens (EN)

International Journal of Computer Mathematics (EN)



*Institutions are responsible for keeping their URLs functional (digital file, item page in repository site)