My main research aims at using artificial intelligence techniques to optimize human learning. In this current era where digital access to knowledge is cheap and user attention is expensive, a number of online applications have been developed for learning. These platforms collect a massive amount of data over various profiles, that can be used to improve learning experience: intelligent tutoring systems can infer what activities worked for different types of students in the past, and apply this knowledge to instruct new students. In order to learn effectively and efficiently, the experience should be adaptive: the sequence of activities should be tailored to the abilities and needs of each learner, in order to keep them stimulated and avoid boredom, confusion and dropout.

Knowledge tracing (KT) is about predicting that the student’s answer the student to some question will be correct or not, given her knowledge state. Computerized adaptive testing (CAT) is about designing a policy to select the next question in a test so that to shorten the test as much as possible to assess the student.

An unexpected side-effect of working on KT and CAT, both research areas involving time-series, is that the machine learning techniques and tools used there are also applicable to many other areas. Having developped a long-term relationship with the Lusis company through projects with CentraleSupélec 3rd year students, we took our relationship to the next level and built a research chair. The topics of this chair involve anomaly detection in time series and reinforcement learning in non-stationary environments.

Google Scholar
HAL Archives Ouvertes

PhD students

currently – Hugo Thimonier Anomaly detection in time-series - Application to fraud detection within credit card transactions. Joint supervision with Bich-Liên Doan and Arpad Rimmel.

currently – Marc Velay Reinforcement learning for portfolio optimization. Joint supervision with Bich-Liên Doan and Arpad Rimmel.

2021 – Benoit Choffin Adaptive spacing algorithms for optimizing long-term mastery of knowledge components. Joint supervision with Yolaine Bourda.

2021 – Julien Hay Representation learning of writing style, application to news recommendation. Joint supervision with Bich-Liên Doan.

2018 – Hiba Hajri Linked Education for Personalization. Joint supervision with Yolaine Bourda.

2016 – Jill-Jenn Vie Construction et analyse de tests adaptatifs dans un cadre de crowdsourcing – Applications aux MOOC. Joint supervision with Yolaine Bourda and Éric Bruillard.

2015 – Youssef Meguebli Leveraging user-generated-content to Enhance and to Personalize News Recommendation. Joint supervision with Bich-Liên Doan.

2013 – Georges Dubus Transformation de programmes logiques : application à la personnalisation et à la personnification d’agents. Joint supervision with Yolaine Bourda.

2006 – Cédric Jacquiot Modélisation logique et générique des systèmes d’hypermédias adaptatifs. Joint supervision with Chantal Reynaud and Yolaine Bourda.

Program comittees, conference organization

Research Projects

2020 – 2024 Chaire Lusis-CentraleSupélec

2017 – 2020 Projet e-FRAN « Parcours Connectés ».

2014 – 2016 Projet FUI NexpertSanté. This project aims at helping people to get back their sleep through Cognitive and Behaviourist Techniques.

2007 – 2010 Projet ITEA2 LINDO. Large scale distributed indexation of multimedia objects.

2007 – 2009 Projet FUI Medi@tic. Diffusion de médias et de services personnalisés.

2002 – 2004 Projet ANR XEmTeX. Diffusion d’une plateforme de production de textes organisée autour de XEmacs et de TEX .

1989 – 1990 EUROTRA Project. Parallelization of the core engine of the automated translation system.

Industrial Projects

I had the opportunity to work with or without students on industrial projects with many companies amng which Alsthom, Hutchinson, Hyperpanel, LUSIS, Microsoft, Quadratec, SFR, Thales, Trialog …

Latest topics include: