Recently, several learning algorithms relying on models with deep architectures have been proposed. Though they have demonstrated impressive performance, to date, they have only b...
Hugo Larochelle, Dumitru Erhan, Aaron C. Courville...
We consider the problem of modeling network interactions and identifying latent groups of network nodes. This problem is challenging due to the facts i) that the network nodes are...
This paper employs the network perspective to study patterns and structures of intraorganizational learning networks. The theoretical background draws from cognitive theories, the...
Standard hybrid learners that use domain knowledge require stronger knowledge that is hard and expensive to acquire. However, weaker domain knowledge can benefit from prior knowle...
The goal of semi-supervised learning (SSL) methods is to reduce the amount of labeled training data required by learning from both labeled and unlabeled instances. Macskassy and Pr...