Variations on the Boltzmann machine
- 7 December 1989
- journal article
- Published by IOP Publishing in Journal of Physics A: General Physics
- Vol. 22 (23) , 5143-5151
- https://doi.org/10.1088/0305-4470/22/23/018
Abstract
The performance of several neural-network-like models for pattern recognition tasks is analysed. A comparison based on recognition of random points in a multidimensional space is made between backpropagation, learning vector quantisation and three variations of Boltzmann machine models. The ordinary Boltzmann machine is found to perform well although at the expense of being time consuming. Replacement of the Monte Carlo method in the Boltzmann machine by a direct formula promises faster evaluation without significant loss of precision.Keywords
This publication has 5 references indexed in Scilit:
- A Learning Algorithm for Boltzmann Machines*Published by Wiley ,2010
- Statistical pattern recognition with neural networksNeural Networks, 1988
- Boltzmann machines for speech recognitionComputer Speech & Language, 1986
- Optimization by Simulated AnnealingScience, 1983
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982