There is interplay between emotions and learning, but this interaction is far more complex than previous learning theories have articulated--this interplay interacts with other re...
State-of-the-art pattern recognition methods have difficulty dealing with problems where the dimension of the output space is large. In this article, we propose a new framework ba...
When modeling high-dimensional richly structured data, it is often the case that the distribution defined by the Deep Boltzmann Machine (DBM) has a rough energy landscape with man...
Standard inductive learning requires that training and test instances come from the same distribution. Transfer learning seeks to remove this restriction. In shallow transfer, tes...
Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...