Improving filling level classification with adversarial training

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.

Container transportation is pivotal in global supply chains, facilitating the exchange of goods between companies across different countries. Given the exceedingly high operational costs of transporting containers, optimizing itinerary schedules can yield ...

Conversational tutoring systems (CTSs) offer a promising avenue for individualized learning support, especially in domains like persuasive writing. Although these systems have the potential to enhance the learning process, the specific role of learner cont ...

Informative sample selection in an active learning (AL) setting helps a machine learning system attain optimum performance with minimum labeled samples, thus reducing annotation costs and boosting performance of computer-aided diagnosis systems in the pres ...

In light of the challenges posed by climate change and the goals of the Paris Agreement, electricity generation is shifting to a more renewable and decentralized pattern, while the operation of systems like buildings is increasingly electrified. This calls ...

This work proposes a decentralized architecture, where individual agents aim at solving a classification problem while observing streaming features of different dimensions and arising from possibly different distributions. In the context of social learning ...

This dataset contains the bulk size-resolved chemical composition and mass concentration of non-refractory submicron aerosols (NR-PM1) measured during the MOSAiC expedition from October 2019 to July 2020. These include the mass concentrations of sulfate (S ...

Laser Powder Bed Fusion (LPBF) is an Additive Manufacturing (AM) process consolidating parts layer by layer, from a metallic powder bed. It allows no limitation in terms of geometry and is therefore of particular interest to various industries. Metallic LP ...

In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...

Uncertainty quantification is a central challenge in reliable and trustworthy machine learning. Naive measures such as last-layer scores are well-known to yield overconfident estimates in the context of overparametrized neural networks. Several methods, ra ...

This study presents a self-supervised Bayesian Neural Network (BNN) framework using air-borne Acoustic Emission (AE) to identify different Laser Powder Bed Fusion (LPBF) process regimes such as Lack of Fusion, conduction mode, and keyhole without ground-tr ...

We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic limit where the number of samples, the input dimension and the network width ...

Deep motion forecasting models have achieved great success when trained on a massive amount of data. Yet, they often perform poorly when training data is limited. To address this challenge, we propose a transfer learning approach for efficiently adapting p ...

The increasing prevalence of personal devices motivates the design of algorithms that can leverage their computing power, together with the data they generate, in order to build privacy-preserving and effective machine learning models. However, traditional ...

Unstructured neural network pruning algorithms have achieved impressive compression ratios. However, the resulting-typically irregular-sparse matrices hamper efficient hardware implementations, leading to additional memory usage and complex control logic t ...

This dataset contains a pollution flag in 1 min time resolution. It is derived by the pollution detection algorithm (PDA) based on the corrected particle number concentration data (DOI upcoming) measured during the year long MOSAiC expedition from October ...

This dataset contains raw particle number concentration data measured during the year long MOSAiC expedition from October 2019 to September 2020. The measurement was performed in the Swiss aerosol container on the D-deck of Research Vessel Polarstern using ...

Artificial intelligence (AI) and machine learning (ML) have become de facto tools in many real-life applications to offer a wide range of benefits for individuals and our society. A classic ML model is typically trained with a large-scale static dataset in ...

Neural networks (NNs) have been very successful in a variety of tasks ranging from machine translation to image classification. Despite their success, the reasons for their performance are still not well-understood. This thesis explores two main themes: lo ...

Designing and implementing online or digital learning material is a demanding task for teachers. This is even more the case when this material is used for more engaged forms of learning, such as inquiry learning. In this article, we give an informed accoun ...

In this work, we resolve a big challenge that most current image quality metrics (IQMs) are unavailable across different image contents, especially simultaneously coping with natural scene (NS) images or screen content (SC) images. By comparison with exist ...

Improving filling level classification with adversarial training

Chattez avec Graph Search

Modelling and solving a real-world truck-trailer scheduling problem in container transportation with separate moving objects

Evaluating the Impact of Learner Control and Interactivity in Conversational Tutoring Systems for Persuasive Writing

GANDALF: Graph-based transformer and Data Augmentation Active Learning Framework with interpretable features for multi-label chest Xray classification

Quantifying the Unknown: Data-Driven Approaches and Applications in Energy Systems

Learning From Heterogeneous Data Based on Social Interactions Over Graphs

Bulk size-resolved chemical composition and mass concentration of non-refractory submicron aerosols measured in the Swiss container during MOSAiC 2019/2020

Towards Robust Monitoring of the Laser Powder Bed Fusion Process based on Acoustic Emission combined with Machine Learning Solutions

Improving Generalization of Pretrained Language Models

On double-descent in uncertainty quantification in overparametrized models

Self-Supervised Bayesian representation learning of acoustic emissions from laser powder bed Fusion process for in-situ monitoring

Bayes-optimal Learning of Deep Random Networks of Extensive-width

Motion Style Transfer: Modular Low-Rank Adaptation for Deep Motion Forecasting

Democratizing Machine Learning

Dynamic Probabilistic Pruning: A General Framework for Hardware-Constrained Pruning at Different Granularities

Pollution mask for the continuous corrected particle number concentration data in 1 min resolution, measured in the Swiss aerosol container during MOSAiC 2019/2020

Continuous raw particle number concentration data in 10 sec resolution, measured in the Swiss aerosol container during MOSAiC 2019/2020

Lifelong Machine Learning with Data Efficiency and Knowledge Retention

Loss landscape and symmetries in Neural Networks

Understanding teacher design practices for digital inquiry-based science learning: the case of Go-Lab

Learning a Unified Blind Image Quality Metric via On-Line and Off-Line Big Training Instances