Deep Belief Networks (DBNs) are hierarchical generative models which have been used successfully to model high dimensional visual data. However, they are not robust to common vari...
We describe a generative model of the relationship between two images. The model is deļ¬ned as a factored threeway Boltzmann machine, in which hidden variables collaborate to deļ...
Joshua Susskind, Roland Memisevic, Geoffrey Hinton...
We present a novel discriminative approach to parsing inspired by the large-margin criterion underlying support vector machines. Our formulation uses a factorization analogous to ...
Ben Taskar, Dan Klein, Mike Collins, Daphne Koller...
Most models of utility elicitation in decision support and interactive optimization assume a predefined set of "catalog" features over which user preferences are express...
We introduce quadratically gated mixture of experts (QGME), a statistical model for multi-class nonlinear classification. The QGME is formulated in the setting of incomplete data,...