Publications associées à Apprentissage par cœur

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

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 ...

Elsevier2024

Optimizing Dynamic Aperture Studies with Active Learning

Tatiana Pieloni, Ekaterina Krymova, Mike Seidel, Davide Di Croce, Massimo Giovannozzi

Dynamic aperture is an important concept for the study of non-linear beam dynamics in circular accelerators. It describes the extent of the phase-space region where a particle's motion remains bounded over a given number of turns. Understanding the feature ...

Iop Publishing Ltd2024

Work in progress: Imagining / Designing informal spaces for learning

Ingrid Le Duc

The paper presents ICAP (interactive, constructive, active and passive) as the theoretical framework to understand the role of informal learning spaces as an active learning tool when students have informal meetings to work on projects. Students in our En ...

Aalborg Universitetsforlag2023

Action Levers towards Sustainable Wellbeing: Re-Thinking Negative Emissions, Sufficiency, Deliberative Democracy

Sascha Nick

Systems theory defines leverage points as places to intervene in order to change a system. Points with high impact on system behavior are notoriously hard to act upon, and indeed most policy intervention is based at the lowest level (#12 in Donella Meadows ...

EPFL2023

A combined genetic algorithm and active learning approach to build and test surrogate models in Process Systems Engineering

François Maréchal, Julia Granacher

In Process Systems Engineering, computationally-demanding models are frequent and plentiful. Handling such complexity in an optimization framework in a fast and reliable way is essential, not only for generating meaningful solutions but also for providing ...

Pergamon-Elsevier Science Ltd2023

Human- and machine-centred designs of molecules and materials for sustainability and decarbonization

Sokseiha Muy, Tian Xie

Data-driven approaches based on high-throughput capabilities and machine learning hold promise in revolutionizing human-centred materials discovery for sustainability and decarbonization. This Review examines the strengths and limitations of different trad ...

NATURE PORTFOLIO2022

VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation

Alexandre Massoud Alahi, Megh Hiren Shukla

Advances in computing have enabled widespread access to pose estimation, creating new sources of data streams. Unlike mock set-ups for data collection, tapping into these data streams through on-device active learning allows us to directly sample from the ...

BMVA Press2022

Active Learning for Imbalanced Civil Infrastructure Data

Diego Matteo Antognini, Adelmo Cristiano Innocenza Malossi, Ioana Giurgiu

Aging civil infrastructures are closely monitored by engineers for damage and critical defects. As the manual inspection of such large structures is costly and time-consuming, we are working towards fully automating the visual inspections to support the pr ...

2022

Active learning for multi-objective optimization of processes and energy systems

François Maréchal, Julia Granacher

In superstructure optimization of processes and energy systems, the design space is defined as the combination of unit considerations, process conditions and model parameters that might be subjected to uncertainty. Most of the time, decision makers are not ...

Elsevier Science2022

Active Learning of Bayesian Probabilistic Movement Primitives

Jean-Marc Odobez, Sylvain Calinon, Hakan Girgin, Thibaut Antoine Kulak

Learning from Demonstration permits non-expert users to easily and intuitively reprogram robots. Among approaches embracing this paradigm, probabilistic movement primitives (ProMPs) are a well-established and widely used method to learn trajectory distribu ...

IEEE2021

Informative sample generation using class aware generative adversarial networks for classification of chest Xrays

Jean-Philippe Thiran

Training robust deep learning (DL) systems for disease detection from medical images is challenging due to limited images covering different disease types and severity. The problem is especially acute, where there is a severe class imbalance. We propose an ...

2019

Learning Approach to Delineation of Curvilinear Structures in 2D and 3D Images

Agata Justyna Mosinska

Detection of curvilinear structures has long been of interest due to its wide range of applications. Large amounts of imaging data could be readily used in many fields, but it is practically not possible to analyze them manually. Hence, the need for automa ...

EPFL2019

DeepFly3D, a deep learning-based approach for 3D limb and appendage tracking in tethered, adult Drosophila

Pascal Fua, Pavan P Ramdya, Helge Jochen Rhodin, Semih Günel, Daniel Eduardo Morales Garza, João Henrique Campagnolo

Studying how neural circuits orchestrate limbed behaviors requires the precise measurement of the positions of each appendage in 3-dimensional (3D) space. Deep neural networks can estimate 2-dimensional (2D) pose in freely behaving and tethered animals. Ho ...

2019

Learning to Reduce Annotation Load

Ksenia Konyushkova

Modern machine learning methods and their applications in computer vision are known to crave for large amounts of training data to reach their full potential. Because training data is mostly obtained through humans who manually label samples, it induces a ...

EPFL2019

Geometry in active learning for binary and multi-class image segmentation

Pascal Fua, Raphael Sznitman, Ksenia Konyushkova

We propose an active learning approach to image segmentation that exploits geometric priors to speed up and streamline the annotation process. It can be applied for both background foreground and multi-class segmentation tasks in 2D images and 3D image vol ...

2019

Efficient Active Learning for Image Classification and Segmentation using a Sample Selection and Conditional Generative Adversarial Network

Jean-Philippe Thiran

Training robust deep learning (DL) systems for medical image classification or segmentation is challenging due to limited images covering different disease types and severity. We propose an active learning (AL) framework to select most informative samples ...

Springer2018

Model-based reinforcement learning and navigation in animals and machines

Dane Sterling Corneil

For decades, neuroscientists and psychologists have observed that animal performance on spatial navigation tasks suggests an internal learned map of the environment. More recently, map-based (or model-based) reinforcement learning has become a highly activ ...

EPFL2018

Learning Active Learning from Data

Pascal Fua, Ksenia Konyushkova, Raphael Sznitman

In this paper, we suggest a novel data-driven approach to active learning (AL). The key idea is to train a regressor that predicts the expected error reduction for a candidate sample in a particular learning state. By formulating the query selection proced ...

2017

Active Learning and Proofreading for Delineation of Curvilinear Structures

Pascal Fua, Agata Justyna Mosinska, Jakub Tarnawski

Many state-of-the-art delineation methods rely on supervised machine learning algorithms. As a result, they require manually annotated training data, which is tedious to obtain. Furthermore, even minor classification errors may significantly affect the top ...

2017

Lower Bounds on Active Learning for Graphical Model Selection

Volkan Cevher, Jonathan Mark Scarlett

We consider the problem of estimating the underlying graph associated with a Markov random field, with the added twist that the decoding algorithm can iteratively choose which subsets of nodes to sample based on the previous samples, resulting in an active ...

2017