Sort by
Refine Your Search
-
Category
-
Program
-
Employer
-
Field
-
The detection of out-of-distribution (OoD) samples is crucial for deploying deep learning (DL) models in real-world scenarios. OoD samples pose a challenge to DL models as they are not represented
-
: Computer science MAIN SUB RESEARCH FIELD OR DISCIPLINES1: Distributed Algorithms – Fault Tolerance – Cloud computing JOB /OFFER DESCRIPTION We are looking for a young researcher interested in fault tolerance and
-
trigger reconstruction architectures for future particle collider experiments, based on deep learning models distributed across multiple hardware processing stages. The mission of this position, based
-
such as distributed generation, interconnection, interaction among local grids and storage, with a particular emphasis on determining exchange prices for energy resources that can stimulate the development
-
Inria, the French national research institute for the digital sciences | Paris 15, le de France | France | 2 months ago
distributed optimization with noisy communication channels, accurately study the selected algorithms, participate in the development and maintenance of the PEPit (https://pepit.readthedocs.io/ ) software
-
Inria, the French national research institute for the digital sciences | Saint Martin, Midi Pyrenees | France | about 1 month ago
Conference on High Performance Computing, Data, and Analytics (HiPC 2017). https://legion.stanford.edu/pdfs/hipc2017.pdf Visibility Algorithms for Dynamic Dependence Analysis and Distributed Coherence. Michael
-
? • comment se comportent-elles face à des données hétérogènes (par exemple, personnalisées ou dont les distributions statistiques ne sont pas identiques dans tous les ensembles de données), ce qui est fréquent
-
learn a monolithic, “black-box” world model, often using a large neural network as function approximators. While these models can be highly effective for prediction within their training distribution
-
Inria, the French national research institute for the digital sciences | Saint Martin, Midi Pyrenees | France | about 1 month ago
follows a phased algorithm: 1) generate an initial training set by uniformly sampling input points 2) (re)train the model on the trainng set 3) use feedback from the model’s performance to generate/augment
-
quality monitoring system. Potential applications will initially focus on drinking water distribution networks. The main sources of water pollution are relatively well documented in the literature