Discovering multiple constraints that are frequently approximately satisfied

Authors:
Geoffrey E. Hinton;Yee-Whye Teh
Affiliations:
Gatsby Computational Neuroscience Unit, University College London, London, England;Department of Computer Science, University of Toronto, Toronto, Ontario, Canada
Venue:
UAI'01 Proceedings of the Seventeenth conference on Uncertainty in artificial intelligence
Year:
2001

Citing 5
Cited 0

Information processing in dynamical systems: foundations of harmony theory

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Learning and relearning in Boltzmann machines

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
An Introduction to Variational Methods for Graphical Models

Machine Learning
Training products of experts by minimizing contrastive divergence

Neural Computation
A decision-theoretic generalization of on-line learning and an application to boosting

EuroCOLT '95 Proceedings of the Second European Conference on Computational Learning Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

Some high-dimensional datasets can be modelled by assuming that there are many different linear constraints, each of which is Frequently Approximately Satisfied (FAS) by the data. The probability of a data vector under the model is then proportional to the product of the probabilities of its constraint violations. We describe three methods of learning products of constraints using a heavy-tailed probability distribution for the violations.