Cette thèse est réalisée dans le cadre du projet BPI DeepTech, en collaboration avec la société Fair&Smart, veillant principalement à la protection des données personnelles conformément au Règlement Général sur la Protection des Données (RGPD). Dans ce contexte, nous avons proposé un modèle neuronal profond pour l'extraction d'informations dans les...
This thesis focuses on graph learning for semi-supervised learning tasks to mitigate the impact of noise in real-world graphs.One approach to learn graphs is using bilevel optimization, whose inner problem optimizes the downstream model, and its outer problem evaluates the performance of the optimized model with respect to a labelling loss and upda...
Le domaine de l'informatique affective, en plein essor depuis quelques décennies, a pour objectif de créer de nouveaux systèmes interactifs capables de percevoir l'état émotionnel de leurs interlocuteurs humains et de s'y adapter automatiquement.Il est de plus en plus fréquent que les datasets ne soient plus disponibles de manière complète et que l...
Les applications d'apprentissage profond se développent rapidement et ne montrent aucun signe de ralentissement. Les topologies des réseaux neuronaux deviennent de plus en plus grandes et complexes pour résoudre les problèmes de la vie réelle.Cette complexité accrue nécessite plus de temps et d'expertise de la part des professionnels, ainsi qu'un i...
Time series is a common data type that has been applied to enormous real-life applications, such as financial analysis, medical diagnosis, environmental monitoring, astronomical discovery, etc. Due to its complex structure, time series raises several challenges in their data processing and mining. The representation of time series plays a key role ...
The phenomenal increase in internet usage, catering to the dissemination of knowledge and expression, has also led to an increase in online hate speech. Online hate speech is anti-social communicative behavior, which leads to the threat and violence towards an individual or a group. Deep learning-based models have become the state-of-the-art soluti...
Published in Pattern recognition
Can one learn to diagnose COVID-19 under extreme minimal supervision? Since the outbreak of the novel COVID-19 there has been a rush for developing automatic techniques for expert-level disease identification on Chest X-ray data. In particular, the use of deep supervised learning has become the go-to paradigm. However, the performance of such model...
Learning with partially labeled data, known as semi-supervised learning, deals with problems where few training examples are labeled while available unlabeled data are abundant and valuable for training. In this thesis, we study this framework in the multi-class classification case with a focus on self-learning and feature selection. Self-learning ...
Published in Computer methods and programs in biomedicine
Deep learning techniques are the state-of-the-art approach to solve image classification problems in biomedicine; however, they require the acquisition and annotation of a considerable volume of images. In addition, using deep learning libraries and tuning the hyperparameters of the networks trained with them might be challenging for several users....
The BigData challenge induces a need for machine learning algorithms to evolve towards large dimensional and more efficient learning engines. Recently, a new direction of research has emerged that consists in analyzing learning methods in the modern regime where the number n and the dimension p of data samples are commensurately large. Compared to ...
