Search

The issue of information diversity – crucial for healthy democratic debates – has been raised recently due to the widespread use of social media as a source of information. These sharing platforms pose many concerns as the information presented to users is not following a usual editorial process and

Graphs are ubiquitous. Also called networks, graphs are used to model many real-world problems and data: social networks, road networks, molecules and genomes, images and 3D objects, etc. Nowadays, many of these applications face a major problem: the volume of data increases to such an extent that

Recent successes of Machine Learning (ML), in particular the deep learning approach, and their growing impact on numerous fields have raised questions about the induced decision process. Indeed, the most efficient models are often overly parameterized black boxes whose inner ruling system is not acc

A hierarchical clustering corresponds to recursively dividing a dataset into increasingly smaller groups. The fundamental assumption of this approach is that the visible structure in the data depends on the chosen scale of observation. This hypothesis has been confirmed, in theory and in practice, o

This project is positioned in the core of the emerging research area on social influence analysis but goes further in trying to demonstrate not only that this framework can be applied to other research domains through a property-driven approach, but also that the algorithmic and strategic aspects pl

- A central objective of SUMM-RE is to build upon extant work exploiting weak supervision to automatically annotate data sets for discourse structure by extending these methods to spontaneous, conversational speech. Quality discourse annotations generally require linguistic expertise - automatic or

Computer Vision is the cornerstone of outdoor applications but most algorithms are still designed to be working in clear weather. The visual artefacts caused by complex adverse weather such as rain, snow and hail were recently proved by us to be deceptive even for the best deep learning techniques.

Machine learning (ML) is ubiquitous in AI-based services and data-oriented scientific fields but raises serious privacy concerns when training on personal data. The starting point of PRIDE is that personal data should belong to the individual who produces it. This requires to revisit ML algorithms t

Our project concerns itself with the activity of the Sun, those events (e.g. flares, coronal mass ejections (CME)) are dynamical phenomena that may have strong impacts on the solar-terrestrial environment. Events of solar activity seem to be strongly associated with the evolution of solar structures

Given the growing awareness of privacy risks of data processing, there is an increasing interest in privacy-preserving learning. However, shortcomings in the state of the art limit the applicability of the privacy-preserving learning paradigm. First, most approaches assume too optimistically a hon

Our project has two goals: a) make machines recognise speech more like humans do, and b) validate our understanding about human speech perception through the use of data-driven techniques. MIM aims at proposing computational models that predict human speech recognition at a fine resolution. Current

In the machine learning field, statistical learning and clustering play a crucial role. Their application in our daily life is no longer to be proven. Besides, technological advances in recording have raised the challenge of managing functional data. For risk assessment, an actual challenge is to de

In a context of data being collected and exploited at huge scales, designing efficient machine learning tools that capture the complexity of data is one of the most important challenges of the decade. Low-rank approximations are such tools, that look for information shared across all modes of a mult

Graph data appear in almost all disciplines. Developing machine learning algorithms for graphs is a crucial task, with a plethora of interdisciplinary applications. As a prominent paradigm, network representation learning aims to embed nodes in a low-dimensional space, preserving the structural prop

The objective is to create a complete three-dimensional digital talking head including the vocal tract from the vocal folds to the lips, the face and integrating the digital simulation of aeroacoustic phenomena. Our project is particularly aimed at learning articulatory gestures from corpora of

Machine learning algorithms are increasingly used to optimize decision making in various areas, but this can result in unacceptable discrimination. The main objective of this project is to propose an innovative framework for the development of learning algorithms that respect fairness constraints. W

The ECOCURL project is grounded in the following hypotheses: • H1: Intrinsically-motivated learning can encourage emergent communication in cooperative multi-agent environments by guiding the agents towards the autonomously discovery of a diverse set of skills for improving their control over the e

A major issue of language processing evaluation metrics concerns the fact that they are designed to globally mesure a proposed solution from a considered reference, with the main objective of being able to compare systems with each other. While automatic systems are aimed at end-users, they are ulti

Autonomous and intelligent embedded solutions are mainly designed as cognitive systems composed of a three step process: perception, decision and action, periodically invoked in a closed-loop manner in order to detect changes in the environment and appropriately choose the actions to be performed ac

Accurate and up-to-date land cover information constitutes key environmental data for developing efficient policies in this era of resource scarcity and climate change. New Satellite Image Times Series offer new opportunities for detecting land cover class transitions. Nevertheless, the challenges o

In the last decade, deep neural networks became state-of-the-art in many computer vision tasks. Nevertheless, their performances are affected when test data are acquired in environments visually different from the data used at training time. Recent domain adaptation techniques are efficient to mitig

Machine learning methods have become prevalent in language technologies. They rely on annotated corpora to train and evaluate models. The CoDeinE project proposes to address the lack of shareable corpora in sensitive domains such as health or banking. The key idea of the project is to define methods

This proposal aims to leverage both the theoretical and the data science pillars, to infer computable models: i ) informed from the existing prior knowledge (Physics first principles and theories); ii ) providing new hints into the principles satisfied by the proposed abstractions, amenable to inte

Early machine learning (ML) and data mining (DM) research tried to fully automate knowledge discovery processes, reducing human intervention. For good reasons: we cannot deal with large amounts of (high-dimensional) data, see patterns everywhere, and technical progress should help save time. Current

Breaking with the current approaches each based on a single analysis paradigm, the HERELLES scientific project proposes to : - Define a generic architecture allowing multi-paradigm methods (supervised vs. unsupervised) potentially working on different data to collaborate and to define the optimal c

Unmanned Aerial Vehicles (UAVs) are becoming essential tools in an increasing number of tasks. However, flying in complex environments requires a fast, low-latency coordination between sensing and control to initiate aggressive maneuvers and allow for flying capabilities such as stabilization, obsta

Huge increase of collected data, storage capacity and computing power promote the field of Artificial Intelligence (AI) to the status of panacea to all problems. Indeed, neural networks improved the results in the fields challenging for the handcrafted algorithms previously. However, there is always

Virtual worlds are increasingly used in the entertainment industry to provide users with a unique and extraordinary experience, in which the quality and the extent of the world is central. This quality is usually obtained by resorting massively to artists, which is expensive and has obvious limitati