Mixed-norm regularization for brain decoding

DOI10.1155/2014/317056MaRDI QIDQ2262456zbMATH OpenOpenAlexWikidataFDO

Authors Rémi Flamary, N. Jrad, Marco Congedo, Alain Rakotomamonjy, Ronald Phlypo

Publication date 16 March 2015

Published in Computational \& Mathematical Methods in Medicine (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1403.3628

Mathematics Subject Classification ID

Biomedical imaging and signal processing (92C55)

Abstract: This work investigates the use of mixed-norm regularization for sensor selection in Event-Related Potential (ERP) based Brain-Computer Interfaces (BCI). The classification problem is cast as a discriminative optimization framework where sensor selection is induced through the use of mixed-norms. This framework is extended to the multi-task learning situation where several similar classification tasks related to different subjects are learned simultaneously. In this case, multi-task learning helps in leveraging data scarcity issue yielding to more robust classifiers. For this purpose, we have introduced a regularizer that induces both sensor selection and classifier similarities. The different regularization approaches are compared on three ERP datasets showing the interest of mixed-norm regularization in terms of sensor selection. The multi-task approaches are evaluated when a small number of learning examples are available yielding to significant performance improvements especially for subjects performing poorly.

Review text

Summary: This work investigates the use of mixed-norm regularization for sensor selection in event-related potential (ERP) based brain-computer interfaces (BCI). The classification problem is cast as a discriminative optimization framework where sensor selection is induced through the use of mixed-norms. This framework is extended to the multitask learning situation where several similar classification tasks related to different subjects are learned simultaneously. In this case, multitask learning helps in leveraging data scarcity issue yielding to more robust classifiers. For this purpose, we have introduced a regularizer that induces both sensor selection and classifier similarities. The different regularization approaches are compared on three ERP datasets showing the interest of mixed-norm regularization in terms of sensor selection. The multitask approaches are evaluated when a small number of learning examples are available yielding to significant performance improvements especially for subjects performing poorly.

Recommendations

• A mixed L2 norm regularized HRF estimation method for rapid event-related fMRI experiments
• Regularized logistic regression and multiobjective variable selection for classifying MEG data
• Single-trial EEG classification via common spatial patterns with mixed Lp- and Lq-norms
• Robust EEG channel selection across subjects for brain-computer interfaces
• Discriminative learning of propagation and spatial pattern for motor imagery EEG analysis

Cites work

• \(Lp\)-norm regularization in volumetric imaging of cardiac current sources
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Convex multi-task feature learning
• Nonnegative mixed-norm convex optimization for mitotic cell detection in phase contrast microscopy
• The Adaptive Lasso and Its Oracle Properties
• Training a Support Vector Machine in the Primal

Cited in

(2)

• Regularized logistic regression and multiobjective variable selection for classifying MEG data
• A mixed L2 norm regularized HRF estimation method for rapid event-related fMRI experiments

This page was built for publication: Mixed-norm regularization for brain decoding

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2262456)