Concept

Adresse électronique

Publications associées (44)

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Connectez-vous pour utiliser Chat avec Graph Search

Test record #04-FR (validation email)

Matthias Wolfgang Bräuninger

Expected subject: [Infoscience] Veuillez vérifier l’affiliation d’une publication Expected body: Bonjour, Une nouvelle publication dans Infoscience a provisoirement été attribuée à votre laboratoire/unité. En tant que lab manager, il vous appartient de con ...

EPFL <> SISB2022

Test record #04-EN (validation email)

Matthias Wolfgang Bräuninger

Expected subject: [Infoscience] Please verify the affiliation of a publication Expected body: Hello, A new record in Infoscience has provisionally been assigned to your lab/unit. As lab manager, it is your responsibility to confirm or deny this affiliation ...

EPFL <> SISB2022

Byzantine Machine Learning Made Easy By Resilient Averaging of Momentums

Rachid Guerraoui, Nirupam Gupta, John Stephan, Sadegh Farhadkhani, Rafaël Benjamin Pinot

Byzantine resilience emerged as a prominent topic within the distributed machine learning community. Essentially, the goal is to enhance distributed optimization algorithms, such as distributed SGD, in a way that guarantees convergence despite the presence ...

PMLR2022

Integrally-Attached Timber Plate Structures: From computational design to robotic construction

Nicolas Henry Pierre Louis Rogeau

This poster provides an overview of the challenges and achievements related to current research led at the Laboratory for Timber Constructions (IBOIS, EPFL) on the robotic assembly of Integrally-Attached Timber Plate Structures (IATPS). The poster is divid ...

2022

, , ,

Microelectromechanical system (MEMS) devices, such as accelerometers, are widely used across industries, including the automotive, consumer electronics, and medical industries. MEMS are efficiently produced at very high volumes using large-scale semiconduc ...

SPRINGERNATURE2022

Pretraining boosts out-of-domain robustness for pose estimation

Alexander Mathis, Mackenzie Mathis, Steffen Schneider, Matthias Bethge, Thomas Ray Biasi, Mert Yüksekgönül

Neural networks are highly effective tools for pose estimation. However, as in other computer vision tasks, robustness to out-of-domain data remains a challenge, especially for small training sets that are common for real-world applications. Here, we probe ...

IEEE COMPUTER SOC2021

GARFIELD: System Support for Byzantine Machine Learning (Regular Paper)

Rachid Guerraoui, Sébastien Louis Alexandre Rouault, Arsany Hany Abdelmessih Guirguis

We present GARFIELD, a library to transparently make machine learning (ML) applications, initially built with popular (but fragile) frameworks, e.g., TensorFlow and PyTorch, Byzantine–resilient. GARFIELD relies on a novel object–oriented design, reducing t ...

IEEE2021

Seismic and Microseismic Signatures of Fluids in Rocks: Bridging the Scale Gap

Lucas Xan Pimienta, Christian David

The aim of this collection is to record a snapshot of our current state of understanding of the impact of fluids on the evolution and monitorability of subsurface rock formations during anthropogenic fluid injection/withdrawal operations, accounting for sc ...

AMER GEOPHYSICAL UNION2019

, ,

The current work addresses a methodology for the optimal design of biogas supply chains based on anaerobic digestion of animal manure. The problem formulation allows the utilization of optimized processing plants that have been previously designed within a ...

Elsevier B.V.2018

Template Induction over Unstructured Email Corpora

Julia Proskurnia

Unsupervised template induction over email data is a central component in applications such as information extraction, document classification, and auto-reply. The benefits of automatically generating such templates are known for structured data, e.g. mach ...