Search for a funded project
Data and Prior, Machine Learning and Control – DeLiCio
We propose to combine machine learning and control theory for sequential decision-making of multiple agents. The project proposes fundamental contributions: adding stability to the algorithms of reinforcement learning; data driven methods for robust control; hybrid ML / CT methods for multi-horizon control and planning; decentralized control. The methodological contributions of this fundamental IA project will be applied to the robust control of UAV fleets
Individual muscle Coordination strategies and their role in the development of musculoskeletal disorders – COMMODE
Our primary testable hypothesis is that each individual has unique muscle coordination strategies that will have specific mechanical effects on his/her MSK system. As such, some strategies would make people more at risk of developing MSK disorders than others.
Mathematics of Stochastic and Deterministic Optimization for Deep Learning – MaSDOL
Machine learning and artificial intelligence are rising themes of research because they have been considered as one way to produce new methods for solving striking challenges in language understanding, advice finding, signal processing, fraud detection. The explosion of datascientist jobs is certainly an evidence of the societal, economic and scientific impact of artificial intelligence. The cornerstone of ML is the use of applied mathematics and in particular, statistics and optimization.
Deep Learning for Constraint Optimization – DELCO
This project aims at building on recent progress in game playing and deep reinforcement learning to design a new generation of more general constraint satisfaction and optimization solvers.
Structure and molecular function of the pseudopilus in type 2 protein secretion pathway – SYNERGY_T2SS
Synergy_T2SS aims to decipher the structure and function or the pseudopilus - the dynamic motor of type II secretion system, and that in three model bacteria.The current models of the secretion mechanism - «piston« and «archimedes' screw« predict different pseudopilus dynamics and interactions with the secreted substrates. We aim to test these prediction using integrative approaches, and to propose a unified and experimentally validated model of type II secretion mechanism.
A new tool for the assessment of Speech Sound Disorders in French-speaking children – EULALIES
stress, and intonation) that may impact speech intelligibility and acceptability’’ (International Expert Panel
Open data, tools and challenges for speaker anonymization – Harpocrates
identifiable information while retaining intelligibility and quality. Anonymized speech signals can
Deciphering continuous MOLecular MOVements of BIOmacromolecular complexes by new cryo-Electron Microscopy image analysis methods – EMBioMolMov
combination with image analysis and artificial intelligence methods. The new approaches will be useful for
Smart machining for controlling part deflection – IMaDe
measurement of the part behavior and defining an intelligent adaptation of the clamping and the positioning [...] contributes to the implementation of so-called intelligent machining adapted to the behavior of the part [...] rebalancing of the residual stresses by means of an intelligent machining clamping system: A literature review
Cooperation between Driver and Intelligent Automated Vehicle – CoCoVeIA
The challenges for automating vehicles in situations other than lane keeping and interdistance regulation require that systems be upgraded to have the necessary skills to control the vehicle in comple