Search for a funded project
Treatment of fake news and informational vagueness: a hybrid approach between deep learning and symbolic AI
of some texts. This hypothesis was tested end of 2021 with the development of a symbolic AI algorithm
Treatment of breast milk by high-pressure processing increases its biological and intestinotropic properties: experimental and clinical studies in preterm newborns.
High pressure processing protects bioactive compounds of human milk and its intestrophic properties
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
Transformations to Groundwater Sustainability : joint learnings from human-groundwater interactions
Billions of people around the world rely for their everyday existence on groundwater. Its invisibility, however, makes groundwater notoriously difficult to govern, also complicating efforts to avoid depletion or pollution. There is an urgent need to creative insights about ways of dealing with the intrinsic tensions that characterize groundwater governance: between individual and collective interests and between short-term gains and longer-term sustainability.
Training Adapted Personalised Affective Social Skills with Cultural Virtual Agents
Training Adapted Personalised Affective Social Skills with Cultural Virtual Agents
Traffic Collection, Contextual Analysis, Data-driven Optimization for 5G
Since 2021, 5G is being deployed worldwide. Its coverage is slowly progressing and is expected to accelerate
Towards visual reasoning in deep learning
In the last decade, Machine Learning and Deep Learning have been at the heart of a technological and scientific revolution. It is a rebirth for Artificial Intelligence with huge advances in automatic translation, audio understanding and computer vision. Driven by these breakthroughs, many application fields are concerned. They involve complex reasoning tasks.<br />L. Bottou discusses several approaches to implement machine reasoning. Following his comments on differences between first order logic reasoning, probabilistic reasoning and others, in this AI chair project, we are focusing on trainable reasoning systems suitable for visual understanding tasks.
Towards more sustainable wastewater treatments: Taking into consideration the TRANSformation PROducts of organic micropollutants
The project addresses the important challenge of better characterizing wastewater treatment processes and intends to study the transformation products (TPs) resulting from the degradation of organic micropollutants during these treatments and subsequently in the natural environment, an aspect that remains neglected in environmental risk assessment. It will contribute to document the treatment performances of innovative solutions allowing to limit sanitary and environmental risks.
Towards exoskeleton-human symbiosis: investigating how humans interact with an upper-limb robotic exoskeleton
The use of robotic exoskeletons is promising in the fields of health and work ergonomics, but the lack of understanding of human motor control in interaction with this type of device remains a factor limiting their effectiveness.
Towards effIcient bloCkchain-based disTributed SDN ArchiteCtures
There is a growing interest in using blockchain within distributed Software Defined Networking (SDN) architectures to address certain limitations such as state synchronization and trust between distributed SDN controllers. The blockchain technology introduces a significant latency that is incompatible with many Internet of Things applications. TIC-TAC-SDN aims at developing a new adaptive consensus protocol to address this problem.
