Zobrazeno 1 - 10
of 888
pro vyhledávání: '"P. Bouvry"'
Distributed learning (DL) leverages multiple nodes to accelerate training, enabling the efficient optimization of large-scale models. Stochastic Gradient Descent (SGD), a key optimization algorithm, plays a central role in this process. However, comm
Externí odkaz:
http://arxiv.org/abs/2410.21491
We often use "explainable" Artificial Intelligence (XAI)" and "interpretable AI (IAI)" interchangeably when we apply various XAI tools for a given dataset to explain the reasons that underpin machine learning (ML) outputs. However, these notions can
Externí odkaz:
http://arxiv.org/abs/2408.12420
The design of satellite missions is currently undergoing a paradigm shift from the historical approach of individualised monolithic satellites towards distributed mission configurations, consisting of multiple small satellites. With a rapidly growing
Externí odkaz:
http://arxiv.org/abs/2408.06903
Alongside the continuous process of improving AI performance through the development of more sophisticated models, researchers have also focused their attention to the emerging concept of data-centric AI, which emphasizes the important role of data i
Externí odkaz:
http://arxiv.org/abs/2407.19784
Autor:
F. Armenta-Cano, A. Tchernykh, J. M. Cortés-Mendoza, R. Yahyapour, A. Yu. Drozdov, P. Bouvry, D. Kliazovich, A. I. Avetisyan, S. Nesmachnow
Publikováno v:
Труды Института системного программирования РАН, Vol 27, Iss 6, Pp 355-380 (2018)
In this paper, we address power aware online scheduling of jobs with resource contention. We propose an optimization model and present new approach to resource allocation with job concentration taking into account types of applications. Heterogeneous
Externí odkaz:
https://doaj.org/article/4684cde1efc34398bf8e5bcc668891a1
Publikováno v:
Bulletin of the Polish Academy of Sciences: Technical Sciences, Vol 66, Iss No 2 (Special Section on Nano- and Micromechanics), Pp 187-191 (2018)
Externí odkaz:
https://doaj.org/article/0d3108a656b44b6587baf89389808013
The substantial increase in AI model training has considerable environmental implications, mandating more energy-efficient and sustainable AI practices. On the one hand, data-centric approaches show great potential towards training energy-efficient A
Externí odkaz:
http://arxiv.org/abs/2402.12010
In the domain of multivariate forecasting, transformer models stand out as powerful apparatus, displaying exceptional capabilities in handling messy datasets from real-world contexts. However, the inherent complexity of these datasets, characterized
Externí odkaz:
http://arxiv.org/abs/2401.00230
Autor:
Simón, Manuel Combarro, Talbot, Pierre, Danoy, Grégoire, Musial, Jedrzej, Alswaitti, Mohammed, Bouvry, Pascal
Publikováno v:
In 29th International Conference on Principles and Practice of Constraint Programming. Leibniz International Proceedings in Informatics (LIPIcs), Volume 280, pp. 44:1-44:15, Schloss Dagstuhl - Leibniz-Zentrum f\"ur Informatik (2023)
Satellite imagery solutions are widely used to study and monitor different regions of the Earth. However, a single satellite image can cover only a limited area. In cases where a larger area of interest is studied, several images must be stitched tog
Externí odkaz:
http://arxiv.org/abs/2312.04210
When engaging in strategic decision-making, we are frequently confronted with overwhelming information and data. The situation can be further complicated when certain pieces of evidence contradict each other or become paradoxical. The primary challen
Externí odkaz:
http://arxiv.org/abs/2311.12604