Hierarchical penalization is a generic framework for incorporating prior information in the fitting of statistical models, when the explicative variables are organized in a hiera...
Marie Szafranski, Yves Grandvalet, Pierre Morizet-...
The need for mining causality, beyond mere statistical correlations, for real world problems has been recognized widely. Many of these applications naturally involve temporal data...
Abstract. We describe a clustering approach with the emphasis on detecting coherent structures in a complex dataset, and illustrate its effectiveness with computer vision applicat...
— Non-negative Matrix factorization (NMF) has increasingly been used as a tool in signal processing in the last couple of years. NMF, like independent component analysis (ICA) is...
Map matching is a fundamental operation in many applications such as traffic analysis and location-aware services, the killer apps for ubiquitous computing. In the past, several m...