Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.
DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.
We propose a new variational inference method based on a proximal framework that uses the Kullback-Leibler (KL) divergence as the proximal term. We make two contributions towards exploiting the geometry and structure of the variational bound. Firstly, we p ...
We study the homogenization problem for the system of equations of dynamics of a mixture of liquid crystals with random structure. We consider a simplified form of the Ericksen-Leslie equations for an incompressible medium with inhomogeneous density with r ...
Despite the massive use of Reclaimed Asphalt Pavement (RAP) in Hot Mix Asphalt (HMA) production, the chemo-physical phenomena that characterise the fabrication of these mixtures have not yet been completely explored. The detection and understanding of thes ...
Easy accessibility can often lead to over-consumption, as seen in food and alcohol habits. On video on-demand (VOD) services, this has recently been referred to as binge watching, where potentially entire seasons of TV shows are consumed in a single viewin ...
Learning analytics (LA) and Educational data mining (EDM) have emerged as promising technology-enhanced learning (TEL) research areas in recent years. Both areas deal with the development of methods that harness educational data sets to support the learnin ...
We study a generalization of Wyner’s Common Information to Watanabe’s Total Correlation. The first minimizes the description size required for a variable that can make two other random variables conditionally independent. If independence is unattainable, W ...
This report presents a study on assisting users in building queries to perform real-time searches in a news and social media monitoring system. The system accepts complex queries, and we assist the user by suggesting related keywords or entities. We do thi ...
Statistical speech recognition has been cast as a natural realization of the compressive sensing and sparse recovery. The compressed acoustic observations are sub-word posterior probabilities obtained from a deep neural network (DNN). Dictionary learning a ...
This paper introduces a dynamic model of the stochastic repayment behavior exhibited by delinquent credit-card accounts. Based on this model, we construct a dynamic collectability score (DCS) which estimates the account-specific probability of collecting a ...
The establishment of thermal diffusion in an Ar-Kr Lennard-Jones mixture is investigated via dynamical non equilibrium molecular dynamics [G. Ciccotti, G. Jacucci, Phys. Rev. Lett. 35, 789 (1975)]. We observe, in particular, the evolution of the density an ...