Méthodes de classification supervisée avec R et Python
Master
Learning deep kernel networks : application to efficient and robust structured prediction
The task of predicting structured objects, e.g. graphs or sequences, is more demanding than the standard supervised regression or classification problems, where the outputs are usually low-dimensional vectors. It has recently attracted a lot of attention in various fields, such as computational biology and chemistry. Such structured spaces are usua...
Amélioration de la prédiction des commandes des pharmacies auprès de la CERP RRM
La CERP Rhin Rhone Méditerranée (CERP RRM) est un grossiste répartiteur qui doit assurer l’approvisionnement de pharmacies. Le secteur du médicament, malgré l'évolution récente de la logistique hospitalière, manque considérablement d'outils d'aide à la décision. Le but de la thèse est de mettre en place un système prédictif pour l’ensemble des clie...
Structure-aware neural networks in the study of multi-modal population cohorts : an application to mental health
It is currently acknowledged that relying solely on conventional classification strategies from a single data source is not effective to understand, diagnose or prognose psychiatric syndromes. The classification targets simply rely on clinician labels that alone do not express a very large variability. In 2009, the Research Domain Criteria (RDoC) r...
Data frugality and computational efficiency in deep learning
This thesis focuses on two challenges of frugality and efficiency in modern deep learning: data frugality and computational resource efficiency. First, we study self-supervised learning, a promising approach in computer vision that does not require data annotations for learning representations. In particular, we propose a unification of several sel...
Deep modeling based on voice attributes for explainable speaker recognition : application in the forensic domain
Automatic speaker recognition (ASpR) has been integrated into critical applications, ranging from customised assistant services to security systems and forensic investigations. It aims to automatically determine whether two voice samples originate from the same speaker. These systems primarily rely on complex deep neural networks (DNN) and present ...
Méthodes et outils d’analyse visuelle pour la compréhension, l’optimisation et l’élaboration de modèles de réseaux de ne...
Les méthodes d’apprentissage profond sont grandement utilisées dans une multitude de domaines de recherche et industriels, notamment pour résoudre des tâches de classification de données. Cependant, cette technologie est souvent associée à un modèle considéré comme une «boîte noire». L’utilisateur peut comprendre les données en entrée et en sortie ...
Contributions à la modélisation procédurale de structures cellulaires stochastoques 2D et à leur génération par l'exempl...
La création de matériaux et de textures procéduraux demande une grande expertise et constitue un travail long, fastidieux et coûteux, c’est pourquoi on cherche à développer des outils permettant leur génération automatique à partir d’exemples en entrée fournis sous la forme d’images : on parle de modélisation procédurale inverse.Dans cette thèse, n...
Dilated convolution with learnable spacings
In this thesis, we develop and study the Dilated Convolution with Learnable Spacings (DCLS) method. The DCLS method can be considered as an extension of the standard dilated convolution method, but in which the positions of the weights of a neural network are learned during training by the gradient backpropagation algorithm, thanks to an interpolat...
MARVEL: MR Fingerprinting with Additional micRoVascular Estimates using bidirectional LSTMs
The Magnetic Resonance Fingerprinting (MRF) approach aims to estimate multiple MR or physiological parameters simultaneously with a single fast acquisition sequence. Most of the MRF studies proposed so far have used simple MR sequence types to measure relaxation times (T1, T2). In that case, deep learning algorithms have been successfully used to s...
