Discovering Multiple Constraints that are Frequently Approximately Satisfied
Geoffrey Hinton, Yee Whye Teh
Some high-dimensional data.sets 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.
PDF Link: /papers/01/p227-hinton.pdf
AUTHOR = "Geoffrey Hinton
and Yee Whye Teh",
TITLE = "Discovering Multiple Constraints that are Frequently Approximately Satisfied",
BOOKTITLE = "Proceedings of the Seventeenth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-01)",
PUBLISHER = "Morgan Kaufmann",
ADDRESS = "San Francisco, CA",
YEAR = "2001",
PAGES = "227--234"