Supervised learning of a parts-based model can be for-
mulated as an optimization problem with a large (exponen-
tial in the number of parts) set of constraints. We show how
thi...
M. Pawan Kumar, Andrew Zisserman, Philip H.S. Torr
Abstract-- This paper introduces a deterministic approximation algorithm with error guarantees for computing the probability of propositional formulas over discrete random variable...
Many of standard practical techniques of solving constraint satisfaction problems use various decomposition methods to represent a problem as a combination of smaller ones. We stu...
: A sequence of increasing translation invariant subspaces can be defined by the Haar-system (or generally by wavelets). The orthogonal projection to the subspaces generates a deco...
We define a probe to be a single action sequence computed greedily from a given state that either terminates in the goal or fails. We show that by designing these probes carefull...