Experiments of Fast Learning with High Order Boltzmann Machines


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.

DOI: 10.1023/A:1008257203142

Extracted Key Phrases

10 Figures and Tables

Cite this paper

@article{Graa1997ExperimentsOF, title={Experiments of Fast Learning with High Order Boltzmann Machines}, author={Manuel Gra{\~n}a and Alicia D'Anjou and F. Xabier Albizuri and Carmen Hern{\'a}ndez and Francisco Javier Torrealdea and A. de la Hera and Ana Isabel Gonz{\'a}lez}, journal={Applied Intelligence}, year={1997}, volume={7}, pages={287-303} }