Samy BengioExpertise
Large Language ModelsReasoningStatistical machine learningSpeech processingPerson authenticationMultimodal processingSequence processingArtificial neural networks, support vector machinesHidden markov models, gaussian mixture modelsetc
Expertise
Large Language ModelsReasoningStatistical machine learningSpeech processingPerson authenticationMultimodal processingSequence processingArtificial neural networks, support vector machinesHidden markov models, gaussian mixture modelsetc
Mission
Samy Bengio
James HendersonTeaching & PhD PhD Students Haruki Shirakami, Dina El Zein, Jose Rafael Espinosa Mena, Kimia Alavi, Mojtaba Nafez Past EPFL PhD Students as codirector Lesly Sadiht Miculicich Werlen, Rabeeh Karimi Mahabadi, Alireza Mohammadshahi, Andreas Thomas Marfurt, Jan Frederik Jonas Florian Mai, Melika Behjati, Fabio James Fehr, Andrei Catalin Coman Courses Deep Learning For Natural Language Processing EE-608 This course covers advanced topics in deep learning architectures for natural language proce
Michaël UnserExpertise
Image Processing, Medical Imaging, Biological Imaging, Wavelets, Splines, Multiresolution
Michael Unser is Full Professor with EPFL’s school of Engineering and the academic director of EPFL's Center for Imaging, Lausanne, Switzerland. His primary areas of investigation are signal processing, biomedical imaging and applied functional analysis. He is internationally recognized for his research contributions to sampling theory, wavelets, the use of splines for image processing, stochastic processes,
Volkan CevherVolkan Cevher received the B.Sc. (valedictorian) in electrical engineering from Bilkent University in Ankara, Turkey, in 1999 and the Ph.D. in electrical and computer engineering from the Georgia Institute of Technology in Atlanta, GA in 2005. He was a Research Scientist with the University of Maryland, College Park from 2006-2007 and also with Rice University in Houston, TX, from 2008-2009. Currently, he is an Associate Professor at the Swiss Federal Institute of Technology Lausanne and a Faculty Fellow in the Electrical and Computer Engineering Department at Rice University. His research interests include machine learning, signal processing theory, optimization theory and methods, and information theory. Dr. Cevher is an ELLIS fellow and was the recipient of the Google Faculty Research award in 2018, the IEEE Signal Processing Society Best Paper Award in 2016, a Best Paper Award at CAMSAP in 2015, a Best Paper Award at SPARS in 2009, and an ERC CG in 2016 as well as an ERC StG in 2011.
Denis GilletDenis Gillet received the Diploma in Electrical Engineering from the Swiss Federal Institute of Technology in Lausanne (EPFL) in 1988, and the Ph.D. degree in Information Systems also from the EPFL in 1995. During 1992 he was appointed as Research Fellow at the Information Systems Laboratory of Stanford University in the United States. He is currently Maître d'enseignement et de recherche at the EPFL School of Engineering, where he leads the React research group. His current research interests include Technologies Enhanced Learning (TEL), Human Computer Interaction (HCI), Human Devices Interaction (HDI) and Optimal Coordination of Complex and Distributed Systems. Denis Gillet is affiliated at EPFL with the Center for Intelligent Systems and the Center for Digital Education.
Pierre VandergheynstPierre Vandergheynst received the M.S. degree in physics and the Ph.D. degree in mathematical physics from the Université catholique de Louvain, Louvain-la-Neuve, Belgium, in 1995 and 1998, respectively. From 1998 to 2001, he was a Postdoctoral Researcher with the Signal Processing Laboratory, Swiss Federal Institute of Technology (EPFL), Lausanne, Switzerland. He was Assistant Professor at EPFL (2002-2007), where he is now a Full Professor of Electrical Engineering and, by courtesy, of Computer and Communication Sciences. As of 2015, Prof. Vandergheynst serves as EPFL’s Vice-Provost for Education. His research focuses on harmonic analysis, sparse approximations and mathematical data processing in general with applications covering signal, image and high dimensional data processing, computer vision, machine learning, data science and graph-based data processing. He was co-Editor-in-Chief of Signal Processing (2002-2006), Associate Editor of the IEEE Transactions on Signal Processing (2007-2011), the flagship journal of the signal processing community and currently serves as Associate Editor of Computer Vision and Image Understanding and SIAM Imaging Sciences. He has been on the Technical Committee of various conferences, serves on the steering committee of the SPARS workshop and was co-General Chairman of the EUSIPCO 2008 conference. Pierre Vandergheynst is the author or co-author of more than 70 journal papers, one monograph and several book chapters. He has received two IEEE best paper awards. Professor Vandergheynst is a laureate of the Apple 2007 ARTS award and of the 2009-2010 De Boelpaepe prize of the Royal Academy of Sciences of Belgium.
Jean-Marc OdobezExpertise
Computer Vision, machine Learning (Bayesian models, deep learning), multimodal processing.Activity analysis, human behavior understanding, human communication, interaction modeling
Dr Jean-Marc Odobez (Msc 1990, PhD 1994) received his Ph.D degree from Rennes University in 1994 for his PhD dissertation done at INRIA. After 5 years as an assistant professor at the University du Maine, France, he decided to join Idiap, where he is now the Head of the Perception & Activity Understanding Group and adju
Nils Bastian SturmaTeaching & PhD Courses Randomization and causation MATH-336 This course covers formal frameworks for causal inference. We focus on experimental designs, definitions of causal models, interpretation of causal parameters and estimation of causal effects.
Sixuan Sven WangTeaching & PhD PhD Students Leonardo Nevali Courses Bayesian statistics MATH-339 A first introduction to Bayesian statistics, assuming knowledge from first courses in statistics and probability. We will focus on foundational statistical and mathematical aspects such as the decision theoretic background, consistency for large sample sizes, and algorithms for Bayesian computation.
Philippe MüllhauptExpertise
Nonlinear Control (Geometry and Algebra)Classical DynamicsRoboticsStatistics
Mission
Provide rigorous technical and scientific training in nonlinear control, classical mechanics, and statistical theory
Current Work
Research and teaching in the fields of control theory, statistics, dynamical systems, and general mechanics.
Philippe Mullhaupt received his Diplôme d Education Ing�nieur | Electricit� 1993 – 1993 EPFL DEA | Automatique et Traitement du Signal 199
Pierre DillenbourgA former teacher in elementary school, Pierre Dillenbourg graduated in educational science (University of Mons, Belgium). He started his research on learning technologies in 1984. In 1986, he has been on of the first in the world to apply machine learning to develop a self-improving teaching system. He obtained a PhD in computer science from the University of Lancaster (UK), in the domain of artificial intelligence applications for education. He has been assistant professor at the University of Geneva. He joined EPFL in 2002. He has been the director of Center for Research and Support on Learning and its Technologies, then academic director of Center for Digital Education, which implements the MOOC strategy of EPFL (over 2 million registrations). He is full professor in learning technologies in the School of Computer & Communication Sciences, where he is the head of the CHILI Lab: "Computer-Human Interaction for Learning & Instruction ». He is the director of the leading house DUAL-T, which develops technologies for dual vocational education systems (carpenters, florists,...). With EPFL colleagues, he launched in 2017 the Swiss EdTech Collider, an incubator with 80 start-ups in learning technologies. He (co-)-founded 4 start-ups, does consulting missions in the corporate world and joined the board of several companies or institutions. In 2018, he co-founded LEARN, the EPFL Center of Learning Sciences that brings together the local initiatives in educational innovation. He is a fellow of the International Society for Learning Sciences. He currently is the Associate Vice-President for Education at EPFL.
Giancarlo Ferrari TrecateExpertise
Automatic control, Dependable control, Neural-network Control, Machine learning, Microgrids, Hybrid systems
Mission
See the webpage of the DECODE (Dependable Control and Decision) group.
Teaching & PhD PhD Students Laura Meroi, Julien Pallage, Nicolas Léo Pierre Kirsch, Simone Baratto, Daniele Martinelli, Riccardo Cescon, Jakob Nylöf, Sabri El Amrani Past EPFL PhD Students Pulkit Nahata, Mustafa Sahin Turan, Baiwei Guo, Jean-Sébastien Brouillon, Clara Galimberti, Andrea Martin, Muhammad Zakwan,
Mats Julius StensrudTeaching & PhD PhD Students Ignacio Gonzalez Perez, Gellért Géza Perényi, Lorenzo Gasparollo, Julien David Laurendeau Past EPFL PhD Students Matias Janvin, Amit Sawant Courses Causal thinking MATH-352 This course will give a unified presentation of modern methods for causal inference. We focus on concepts, and we will present examples and ideas from various scientific disciplines, including medicine, computer science, engineering, economics and epidemiology. Probability and statistics (
Aude BillardExpertise
RoboticsMachine LearningArtificial IntelligenceHuman-Robot InteractionMechatronicsDynamical Systems ControlComputational Neuroscience
Aude Billard is full professor and head of the LASA laboratory at the School of Engineering at the Swiss Institute of Technology Lausanne (EPFL), and the Director of the Swiss Innovation Booster on Robotics. Dr. Billard acts as the President of the IEEE Robotics and Automation Society (RAS), after serving in several roles in the administrative and executive committe
Giovanni De MicheliExpertise
Design technologies for integrated systems on silicon, such as synthesis, hw/sw codesign and low-power design, as well as systems on heterogeneous platforms including electrical and biological components.
Scientific Director of EcoCloud Center at EPFL
Directing activities towards creating sustainable computation including AI.Designing energy-savvy data centers and edge devices.
More information
Please read http://si2.epfl.ch/~demichel/
Giovanni De Micheli is a research scientist in electronics and Pascal FrossardTeaching & PhD PhD Students Yiming Qin, Alba Carballo Castro, Elisa Messori, Ke Wang, Sevda Ögüt, Tuna Alikasifoglu, William Cappelletti, Manuel Madeira, Mahdi Amiri, Ortal Yona Senouf, Vasiliki Rizou, Cem Bilaloglu, Abdellah Rahmani, Amel Abdelraheem, Jérémy Jean Philippe Baffou, Adam Hazimeh, Vincent Jung, Yike Zhao Past EPFL PhD Students Dan Jurca, Jean-Paul Wagner, Ivana Radulovic, Ivana Tosic, Effrosyni Kokiopoulou, Zafer Arican, Vijayaraghavan Thirumalai, Tamara Tosic, Eirina Bourtsoulatze, Elif Vur
François MaréchalPh D. in engineering Chemical process engineer
Researcher and lecturer in the field of computer aided process and energy systems engineering.
Lecturer in the mechanical engineering, electrical engineering and environmental sciences engineering in EPFL.
I'm responsible for the Minor in Energy of EPFL and I'm involved in 3 projects of the Competence Center in Energy and Mobility (2nd generation biofuel, Wood SOFC, and gas turbine development with CO2 mitigation) in which i'm contributing to the energy conversion system design and optimisation.
Short summary of my scientific carrer
After a graduation in chemical engineering from the University of Liège, I have obtained a Ph. D. from the University of Liège in the LASSC laboratory of Prof. Kalitventzeff (former president of the European working party on computer aided process engineering). This laboratory was one of the pioneering laboratory in the field of Computer Aided Process Engineering.
In the group of Professor Kalitventzeff, I have worked on the development and the applications of data reconciliation, process modelling and optimisation techniques in the chemical process industry, my experience ranges from nuclear power stations to chemical plants. In the LASSC, I have been responsible from the developments in the field of rational use of energy in the industry. My first research topic has been the methodological development of process integration techniques, combining the use of pinch based methods and of mathematical programming: e.g. for the design of multiperiod heat exchanger networks or Mixed integer non linear programming techniques for the optimal management of utility systems. Fronted with applications in the industry, my work then mainly concentrated on the optimal integration of utility systems considering not only the energy requirements but the cost of the energy requirements and the energy conversion systems. I developed methods for analysing and integrating the utility system, the steam networks, combustion (including waste fuel), gas turbines or other advanced energy conversion systems (cogeneration, refrigeration and heat). The techniques applied uses operation research tools like mixed integer linear programming and exergy analysis. In order to evaluate the results of the utility integration, a new graphical method for representing the integration of the utility systems has been developed. By the use of MILP techniques, the method developed for the utility integration has been extended to handled site scale problems, to incorporate environmental constraints and reduce the water usage. This method (the Effect Modelling and Optimisation method) has been successfully applied to the chemical plants industry, the pulp and paper industry and the power plant. Instead of focusing on academic problems, I mainly developed my research based on industrial applications that lead to valuable and applicable patented results. Recently the methods developed have been extended to realise the thermoeconomic optimisation of integrated systems like fuel cells. My present R&D work concerns the application of multi-objective optimisation strategies in the design of processes and integrated energy conversion systems.
Since 2001, Im working in the Industrial Energy Systems Laboratory (LENI) of Ecole Polytechnique fédérale de Lausanne (EPFL) where Im leading the R&D activities in the field of Computer Aided Analysis and Design of Industrial Energy Systems with a major focus on sustainable energy conversion system development using thermo-economic optimisation methodologies. A part from the application and the development of process integration techniques, that remains my major field of expertise, the applications concern :
Rational use of water and energy in Industrial processes and industrial production sites : projects with NESTLE, EDF, VEOLIA and Borregaard (pulp and paper).Energy conversion and process design : biofuels from waste biomass (with GASNAT, EGO and PSI), water dessalination and waste water treatment plant (VEOLIA), power plant design (ALSTOM), Energy conversion from geothermal sources (BFE). Integrated energy systems in urban areas : together with SCANE and SIG (GE) and IEA annexe 42 for micro-cogeneration systems.
I as well contributed to the definition of the 2000 Watt society and to studies concerning the emergence of green technologies on the market in the frame of the Alliance for Global Sustainability.
Sébastien MarcelExpertise
image processing, pattern recognition, machine learning, biometrics
Current work
Face recognitionSpeaker recognitionMobile biometrics ( http://www.mobioproject.org )Spoofing ( http://www.tabularasa-euproject.org )Biometrics evaluation and testing ( http://www.beat-eu.org )
Sébastien Marcel is the head of the Biometrics group and senior research scientist at the Idiap Research Institute (CH), where he leads a research team and conducts research on biometrics and more particularly face recognition, Alexandre Massoud AlahiAlexandre Alahi is currently an Assistant Professor at EPFL. He spent five years at Stanford University as a Post-doc and Research Scientist after obtaining his Ph.D. from EPFL. His research enables machines to perceive the world and make decisions in the context of transportation problems and smart environments. He has worked on the theoretical challenges and practical applications of socially-aware Artificial Intelligence, i.e., systems equipped with perception and social intelligence. He was awarded the Swiss NSF early and advanced researcher grants for his work on predicting human social behavior. He won the CVPR Open Source Award (2012) for his work on Retina-inspired image descriptors, and the ICDSC Challenge Prize (2009) for his sparsity-driven algorithm that has tracked more than 100 million pedestrians to date. His research has been covered internationally by BBC, abc, PBS, Euronews, Wall street journal, and other national news outlets around the world. Alexandre has also co-founded multiple startups such as Visiosafe, and won several startup competitions. He was elected as one of the Top 20 Swiss Venture leaders in 2010.
