Search for a funded project
CooperAtive MachinE Learnning and OpTimization – CAMELOT
The goal of the Chaire CaMeLOt is to address the modern challenges of crowd-sourcing, peer-grading and to provide a unified mathematical framework and efficient algorithms to cope with cooperative and decentralized learning and optimization.
Intégration et Développement à Aix-Marseille par la formation
XXIème siècle. Initié en seconde partie de l’année 2021, IDeAL s’articule autour de 3 programmes :
Transformer et innover dans la formation graduate via la recherche
(IE) qui ont intégré le projet lors de l'année 2021-2022, dans le cadre de l'Appel à Manifestation d'Intérêt
Core integration of novel functional, adaptive materials into a smart, highly sensitive analytical system for point of need environmental applications – SmartMatter
SmartMatter proposes novel functional materials featuring magneto-plasmonic properties and validated capability for boosting sensitivity to environmentally relevant analytes. Adaptive 3D-nanoplatforms will enhance the analytic response of (magneto)optical waveguides sensing chips encompassing analyte specific interaction sites.
Learning Reasoning, Memory and Behavior – REMEMBER
We will focus on methodological contributions (models and algorithms) for training virtual and real agents to learn to solve complex tasks autonomously, targeting terrestrial mobile robots, typically service robots; industrial cobotics; autonomous vehicles; UAVs; humanoid robots. In particular, intelligent agents require high-level reasoning capabilities, situation awareness, and the capacity of robustly taking the right decisions at the right moments. The required behavior policies are complex, since they involve high-dimensional input spaces and state spaces, partially observed problems, as well as highly non-linear and entangled interdependencies. Learning them crucially depends on the algorithm’s capacity of learning compact, structured and semantically meaningful memory representations, which are able to capture short and long range regularities in the task and the environment. A second key requirement is the ability to learn these representations with a minimal amount of human interventions and annotations, as the manual design of complex representations is up to impossible. This requires the efficient usage of raw data through the discovery of regularities by different means: supervised, unsupervised or self-supervised learning, through reward or intrinsic motivation etc.
Using the variability of the human cortical folding pattern to benchmark unsupervised learning – FOLDDICO
There are more than seven billion humans alive today, who have both unique fingerprints and unique cortical folding patterns. Nobody knows whether the variability in these cortical folding patterns has a meaning, or even where these patterns, which appear in utero, come from. It is time for machine learning to try to decipher these folding patterns.
Forms of life in the megapolis: Miletus in the longue durée – MegaMil
A social archaeology on a large ancient city
DeepCuriosity: Curiosity-driven exploration and curriculum learning in AI with applications to autonomous agents, automated discovery and educational technologies. – DeepCuriosity
Curiosity-driven exploration and curriculum learning in AI with applications to autonomous agents, automated discovery and educational technologies
Gender and health inequalities in CONSTANCES: social determinants of the male-female differences in healthy ageing – GINCO
Social determinants of healthy ageing in women and men<br /><br />The GINCO project focuses on the social determinants at the intersection of the professional, social and family spheres. Using data from the CONSTANCES cohort, it is based on a life-course approach to health determinants. Its aim is to suggest levers for action, particularly through public policies, to improve the chances of ageing in good health and reduce inequalities.
The vestibular system: a hidden sense for a core sense of self – VESTISELF
Hidden and pre-conscious, the vestibular sense does not pertain to the five traditional Aristotelian senses. Yet, it impacts human development, perception, action, and cognition.
