Publications associées à Classifieur linéaire

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Alexandre Massoud Alahi, Mohamed Ossama Ahmed Abdelfattah, Mariam Ahmed Mahmoud Hegazy Hassan

Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...

2024

VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction

Sabine Süsstrunk, Tong Zhang, Yufan Ren

The success of the Neural Radiance Fields (NeRF) in novel view synthesis has inspired researchers to propose neural implicit scene reconstruction. However, most existing neural implicit reconstruction methods optimize perscene parameters and therefore lack ...

2024

Error scaling laws for kernel classification under source and capacity conditions

Florent Gérard Krzakala, Lenka Zdeborová, Hugo Chao Cui, Bruno Loureiro

In this manuscript we consider the problem of kernel classification. While worst-case bounds on the decay rate of the prediction error with the number of samples are known for some classifiers, they often fail to accurately describe the learning curves of ...

2023

The statistical complexity of early-stopped mirror descent

Tomas Vaskevicius, Varun Kanade

Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms. In this paper, we study the statistical guarantees on the excess risk achieved by early-stopped unconstrain ...

Oxford2023

Spectral representation of EEG data using learned graphs with application to motor imagery decoding

Dimitri Nestor Alice Van De Ville, Hamid Behjat, Maliheh Miri

Electroencephalography (EEG) data entail a complex spatiotemporal structure that reflects ongoing organi-zation of brain activity. Characterization of the spatial patterns is an indispensable step in numerous EEG processing pipelines. We present a novel me ...

Oxford2023

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

Rita Drissi Daoudi

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 ...

EPFL2023

Learnable Wavelet Transform and Domain Adversarial Learning for Enhanced Bearing Fault Diagnosis

Olga Fink, Gaëtan Michel Frusque, Qi Li, Baorui Dai

The application of unsupervised domain adaptation (UDA)-based fault diagnosis methods has shown significant efficacy in industrial settings, facilitating the transfer of operational experience and fault signatures between different operating conditions, di ...

Research Publishing2023

Smart filter aided domain adversarial neural network for fault diagnosis in noisy industrial scenarios

Olga Fink, Gaëtan Michel Frusque, Tianfu Li, Qi Li, Baorui Dai

The application of unsupervised domain adaptation (UDA)-based fault diagnosis methods has shown significant efficacy in industrial settings, facilitating the transfer of operational experience and fault signatures between different operating conditions, di ...

2023

Gyrokinetic simulation of low-n Alfvenic modes in tokamak HL-2A plasmas

Javier García Hernández, Samuele Mazzi

The turbulence characteristics of plasmas with internal transport barriers in the HL-2A tokamak are analyzed by means of linear gyrokinetic simulations. It is found that turbulence is dominated by the ion temperature gradient (ITG) mode together with large ...

2023

Kernel Density Estimation of Electromyographic Signals and Ensemble Learning for Highly Accurate Classification of a Large Set of Hand/Wrist Motions

Parviz Ghaderi

The performance of myoelectric control highly depends on the features extracted from surface electromyographic (sEMG) signals. We propose three new sEMG features based on the kernel density estimation. The trimmed mean of density (TMD), the entropy of dens ...

FRONTIERS MEDIA SA2022

Classifieur linéaire

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction

Error scaling laws for kernel classification under source and capacity conditions

The statistical complexity of early-stopped mirror descent

Spectral representation of EEG data using learned graphs with application to motor imagery decoding

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

Learnable Wavelet Transform and Domain Adversarial Learning for Enhanced Bearing Fault Diagnosis

Smart filter aided domain adversarial neural network for fault diagnosis in noisy industrial scenarios

Gyrokinetic simulation of low-n Alfvenic modes in tokamak HL-2A plasmas

Kernel Density Estimation of Electromyographic Signals and Ensemble Learning for Highly Accurate Classification of a Large Set of Hand/Wrist Motions

Graph Chatbot

Chattez avec Graph Search

Spectral representation of EEG data using learned graphs with application to motor imagery decoding

The statistical complexity of early-stopped mirror descent

Gyrokinetic simulation of low-n Alfvenic modes in tokamak HL-2A plasmas

VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Kernel Density Estimation of Electromyographic Signals and Ensemble Learning for Highly Accurate Classification of a Large Set of Hand/Wrist Motions

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

Learnable Wavelet Transform and Domain Adversarial Learning for Enhanced Bearing Fault Diagnosis

Smart filter aided domain adversarial neural network for fault diagnosis in noisy industrial scenarios

Error scaling laws for kernel classification under source and capacity conditions