ZIB

Treffer pro Seite

Treffer 1 - 1 | 1 Treffer

Sortierung

Digitale Medien

Experiments of Fast Learning with High Order Boltzmann Machines (1997)

Gra~na, M. ; D'Anjou, A. ; Albizuri, F.X. ; [weitere]

Springer

Applied intelligence 7 (1997), S. 287-303

zur Merkliste hinzufügen auf der Merkliste

Details

ISSN: 1573-7497

Schlagwort(e): Neural Networks ; Boltzmann Machines ; High Order networks ; Classification Problems

Quelle: Springer Online Journal Archives 1860-2000

Thema: Informatik

Notizen: Abstract This work reports the results obtained with the application of High Order Boltzmann Machines without hidden units to construct classifiers for some problems that represent different learning paradigms. The Boltzmann Machine weight updating algorithm remains the same even when some of the units can take values in a discrete set or in a continuous interval. The absence of hidden units and the restriction to classification problems allows for the estimation of the connection statistics, without the computational cost involved in the application of simulated annealing. In this setting, the learning process can be sped up several orders of magnitude with no appreciable loss of quality of the results obtained.

Materialart: Digitale Medien

URL: http://dx.doi.org/10.1023/A:1008257203142

Permalink

Bibliothek	Standort	Signatur	Band/Heft/Jahr	Verfügbarkeit

Andere fanden auch interessant ...

Artikel (Nationallizenzen)

Volltext

Treffer 1 - 1 | 1 Treffer