Existing online learning experiences lack the social dimension that characterizes learning in the real world. This social dimension extends beyond the traditional classroom into t...
Learning models for detecting and classifying object categories is a challenging problem in machine vision. While discriminative approaches to learning and classification have, in...
We present a new estimation principle for parameterized statistical models. The idea is to perform nonlinear logistic regression to discriminate between the observed data and some...
Generative models such as statistical language modeling have been widely studied in the task of expert search to model the relationship between experts and their expertise indicat...
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to use...
Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pi...