The University of the Digital Society is based on interactions that facilitate learning in a new pragmatic context. Catalysts involved in the learning process replace the traditio...
This paper treats tracking as a foreground/background classification problem and proposes an online semisupervised learning framework. Initialized with a small number of labeled ...
We propose and analyze a distribution learning algorithm for a subclass of Acyclic Probabilistic Finite Automata (APFA). This subclass is characterized by a certain distinguishabi...
: As scan compression replaces the traditional scan it is important to understand how it works with power. DFT MAX represents one of the two primary scan compression solutions used...
—Triggered by a market relevant application that involves making joint predictions of pedestrian and public transit flows in urban areas, we address the question of how to utili...
Marion Neumann, Kristian Kersting, Zhao Xu, Daniel...