The product of experts learning procedure [1] can discover a set of stochastic binary features that constitute a nonlinear generative model of handwritten images of digits. The qua...
Various methods have been proposed in the past to improve student learning by introducing new styles of working with assignments. These include problem-based learning, use of case...
This paper describes the winning entry to the Omphalos context free grammar learning competition. Our approach integrates an information theoretic constituent likelihood measure to...
We consider a supervised learning setting in which the main cost of learning is the number of training labels and one can obtain a single label for a bag of examples, indicating o...
In this paper we present a method for learning classspecific
features for recognition. Recently a greedy layerwise
procedure was proposed to initialize weights of deep
belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...