-
techniques and the structure of bilevel problems in large-scale settings. Objectives The goal of this postdoctoral project is to develop scalable blackbox optimization algorithms tailored to bilevel problems
-
suitable data models [CSC+23]. Objectives As far as the design of efficient numerical algorithms in an off-the-grid setting is concerned, the problem is challenging, since the optimization is defined in
-
] and taphonomy of animal bones [Cifuentes-Alcobendas and Dom´ınguez-Rodrigo, 2019] are gradually intensifying. Thus, the present PhD project is an opportunity for the development of original ML solutions
-
. Côte d’Azur & INRIA), will be focused on the development and the understanding of deep latent variables models for unsupervised learning with massive heterogenous data. Although deep learning methods and
-
of persistent AF. However, this therapy depends heavily on the practitioner’s subjectivity, with rather variable protocols and success rates reported by different centers. The development of robust, widely
-
algorithms will be developed to extract discriminative and predictive features from a multimodal dataset consisting of digital histopathological images, lung CT images, clinical, genomics, and multiproteomics
-
expertise [2]. Unlike scheduled orthopedic procedures, trauma surgery has seen little integration of artificial intelligence in preoperative planning. Currently, identifying bone fragments and determining
-
diagnostics, decision-making, and surgical procedures. To assess their usability through different application tools, the lab conducts stress tests under real conditions and develops multiparametric usability
-
motivated the development of Federated Learning (FL) [1,2], a framework for on-device collaborative training of machine learning models. FL algorithms like FedAvg [3] allow clients to train a common global
-
train robust machine learning (ML) algorithms without exchanging the actual data. The benefits of such a decentralized technology over personal and confidential data are multiple and already include some