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.
The visual inspection of existing infrastructure is a critical step for asset management, as the detection and quantification of damage must be useful to prioritise maintenance. In Switzerland, main inspections are made every five years for all road bridge ...
It is a complex task to evaluate the effects of a river rehabilitation measure on the riverscape’s habitat mosaic. This study investigated the medium term effects of a rehabilitation measure in a residual flow reach downstream of a hydroelectric dam. The r ...
Introduction: Early diagnosis and early treatment have become the gold standard for management of developmental dysplasia of the hip. Surgery is required in case of failed initial treatment. Innominate pelvic osteotomy of Salter (SIO), Pemberton's pericaps ...
Recent advances on Vision Transformer (ViT) and its improved variants have shown that self-attention-based networks surpass traditional Convolutional Neural Networks (CNNs) in most vision tasks. However, existing ViTs focus on the standard accuracy and com ...
MLsub extends traditional Hindley-Milner type inference with subtyping while preserving compact principal types, an exciting new development. However, its specification in terms of biunification is difficult to understand, relying on the new concepts of bi ...
Many decisions rely on how we evaluate potential outcomes and estimate their corresponding probabilities of occurrence. Outcome evaluation is subjective because it requires consulting internal preferences and is sensitive to context. In contrast, probabili ...
Investigators often evaluate treatment effects by considering settings in which all individuals are assigned a treatment of interest, assuming that an unlimited number of treatment units are available. However, many real-life treatments are of limited supp ...
Even the largest neural networks make errors, and once-correct predictions can become invalid as the world changes. Model editors make local updates to the behavior of base (pre-trained) models to inject updated knowledge or correct undesirable behaviors. ...
The impact of optical noises on the performance of coded Brillouin optical time-domain analyzers is modelled and experimentally demonstrated. This enables quantitatively evaluating the actual coding gain at any point along the sensing fiber. ...
This paper introduces a new approach to reduce end-to-end costs in large-scale replicated systems built under a Byzantine fault model. Specifically, our approach transforms a given replicated state machine (RSM) to another RSM where nodes incur lower costs ...
