Search
CooperAtive MachinE Learnning and OpTimization – CAMELOT
Firstly, we aim at addressing challenges in crowd-sourcing biodiversity identification. Biodiversity informatics is a relatively young discipline (the term was coined in the early 1990’s) that typically builds on taxonomic, biogeographic, or ecological information stored in digital form. Pl@ntNet [
Learning Reasoning, Memory and Behavior – REMEMBER
We use large scale machine learning (ML) address problems in robotics: - Learning of spatial reasoning - Integration of classical planning and learned planning - Integration of physics into ML - Sim2real transfer: large-scale learning in simulation and deployment to real physical environments -
Towards visual reasoning in deep learning – VISA DEEP
In this AI chair, we propose to investigate tasks of visual reasoning beyond merely ImageNet classification. It is required to decline some reasoning processes in the visual analysis scheme. We intend to explore the combination of elementary reasoning blocks into deep architectures. We want to quest
Tools for automated, symbolic analysis of real-world cryptographic protocols – ASAP
The goal of this project is the development of efficient algorithms and tools for automated verification of cryptographic protocols, that are able to comprehensively analyse detailed models of real-world protocols building on techniques from automated reasoning. Automated reasoning is the subfield o
Explainable artificial intelligence for anti-money laundering – XAIforAML
Financial institutions and government authorities want to introduce more advanced AI tools in AML-CFT processes. Financial institutions see AI as a way to reduce costs. Regulators see AI as a way to identify more criminal networks that currently escape prosecution (the director of Europol estimates
Sequential and Active Learning for Optimization – SeqALO
The goal of this project is to develop a new theory of sequential and active optimization, to implement it in industrial projects, and to develop a teaching track dedicated to machine learning in general and to sequential decision theory in particular within the ENS of Lyon. Let f:X*E?R be a stoc
Analyzing Large Scale Geometric Data Collections – AIGRETTE
Our ultimate goal is to design novel learning techniques capable both of handling geometric data directly and of combining and integrating different data sources into a unified analysis pipeline. Achieving these goals will require developing new techniques for both representing geometric data in
Belief Change for Better Multi-Source Information Analysis – BE4musSIA
* Improve belief revision operators * Improve belief merging operators * Develop measures of inconsistency and measures of conflicts * Apply all of these tools to multi-source information analysis * Illustrate the tools developed in this project within on the semantic web, in order to improve qu
Using the variability of the human cortical folding pattern to benchmark unsupervised learning – FOLDDICO
In mainstream brain mapping methodologies, the variability of the cortical folding pattern is treated as noise, and is cancelled out as far as possible when warping each brain to a template. However, some research groups consider that cortical folding could become a useful proxy for cortical archite
Knowledge And Representation Integration on the Brain – KARAIB
To tackle this challenge, we propose to leverage rapidly increasing data sources: text and brain locations described in neuroscientific publications, brain images and their annotations taken from public data repositories, and several reference datasets. Our aim here is to develop multi-modal ma
Shared-Control Algorithms for Human/Multi-Robot Cooperation – MULTISHARED
Robots perform actions in the real world according to their perception and understanding of the environment, as they physically interact with it. The ensemble of these abilities of sensing, interpreting, modelling, predicting, and interacting with the physical world are concrete applications of Arti
Bridging Artificial Intelligence and Neuroscience – BrAIN
Artificial intelligence (AI) with recent progress in statistical machine learning (ML) is currently aiming to revolutionise how experimental science is conducted. In physics, chemistry, biology, neuroscience or medicine, data is now the driver of new theoretical insights and new scientific hypothese
Modeling and Extracting Complex Information from Natural Language Text – NoRDF
We want to enrich knowledge bases with events, causation, conditions, precedence, stories, negation, and beliefs. In particular, we will investigate the expression of sentiment. We want to extract this type of information at scale from structured and unstructured sources, and we want to allow mac
Security of AI for Defense Applications – SAIDA
The Villani report emphases the utmost importance of mastering AI in defense and security applications. France must keep an advantage in AI over its adversaries and be technologically on par with its Allies. A dependence to non-European technology providers is a national threat. The main utility
Generating Text in Multiple Languages from Multiple Sources – XNLG
Natural Language Generation (NLG) produces text from data, text or meaning representations. With the boom of AI and deep learning technology, the field of NLG has been growing at exponential speed. While NLG has many potential applications (summarization, data verbalisation, text simplification, r
Bayesian learning of expensive models, with applications to cell biology – Baccarat
Expensive computer simulations have become routine in the experimental sciences. Astrophysicists design complex models of the evolution of galaxies, biologists develop intricate models of cells, ecologists model the dynamics of ecosystems at a world scale. A single evaluation of such complex models
Fast inference with controlled uncertainty: application to astrophysical observations. – SHERLOCK
SHERLOCK is targeted as a balanced research and training project. Its originality lies in 3 main motivations: a promising research project in AI with interdisciplinary applications in astrophysics and chemistry, an ambitious training program connected to high-level research-oriented master programs,
Earth Observation with Optimal Transport for Artificial Intelligence – OTTOPIA
Earth Observation, whether it be by satellites, airborne captors or drones, allows a better understanding of the dynamics of environmental systems or our human society. It is a decisive tool to measure the impact of mankind on earth. In the last 50 years, the fast development of spatial missions and
Automatic Endoscopic Scene Assessment for Safety Checkpoint Validation in the Operating Room – AI4ORSafety
The project AI4ORSafety aims at proposing new computer vision and machine learning methods for the analysis of endoscopic videos so as to build an AI system for the operating room that can automatically monitor safety checkpoints. This project will focus on a high-impact and high-visibility clinical
Learning data integration, from discrete entities to signals – LearnI
With data science, machine learning is changing how decisions are made in many fields such as health or business. However, the bottleneck is often not in the statistical analysis but in combining data of different nature or from different sources. Indeed, data integration still relies heavily on hum
A road toward safe artificial intelligence in mobility – Raimo
Recent progresses in machine learning in general ad deep learning in particular make it possible to include this technology in more and more autonomous vehicles. However, before this possible future becomes reality and our roads are made safer with algorithms replacing human drivers, it is necessar
Intelligent Analysis and Interconnexion of Heterogeneous Contents in Digital Arenas – SourcesSay
Digital data, whether text (news articles), semi-structured (tweets, other social media content) or structured (RDF or CSV files) are produced and shared at very large speed today. As data brings a digital mirror of human activity, in particular democracy and public debate, intelligently exploiting
ADvanced Submarine Intelligent Listening – ADSIL
This chair opens the paradigm "ADvanced Submarine Intelligent Listening". It is headed by honorary member IUF member H. Glotin. His 3 LIS colleagues in Toulon are experts in Deep Learning and acoustics / bioacoustics. This team had particular discussed this topic when they received Y. Lecun in 2013