Sort by
Refine Your Search
-
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
-
revisit discretization methodologies in view of modern requirements and computational capabilities. The candidate will focus on developing mesh generation algorithms meeting the following criteria
-
. The monitoring of telecommunications and energy production and distribution networks are characteristic examples of such time-critical applications. The project aims to propose unsupervised online CPD algorithms
-
, sensor failures, or the aggregation of datasets from multiple sources. There is a rich literature on how to impute missing values, for example, considering the EM algorithm [Dempster et al., 1977], low
-
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
-
training of an artificial intelligence algorithm capable of automatically segmenting the bony structures of both healthy and fractured tibial plateaus. This will serve three main purposes: 1) Enable
-
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
-
, transport, or defense. On the technical side, we aim at combining statistical latent variable models with deep learning algorithms to justify existing results and allow a better understanding of their
-
the technical side, we aim at combining statistical latent variable models with deep learning algorithms to justify existing results and allow a better understanding of their performances and their limitations
-
research work will be to devise efficient algorithms for source separation in DAS measurements. Issues such as large data volumes that can exceed 1 To per day and per fiber, instrument noise, complex nature