Filters








6,252 Hits in 3.5 sec

Mixed-Norm Regularization for Brain Decoding

R. Flamary, N. Jrad, R. Phlypo, M. Congedo, A. Rakotomamonjy
2014 Computational and Mathematical Methods in Medicine  
This work investigates the use of mixed-norm regularization for sensor selection in event-related potential (ERP) based brain-computer interfaces (BCI).  ...  The different regularization approaches are compared on three ERP datasets showing the interest of mixed-norm regularization in terms of sensor selection.  ...  [34] by studying general mixed-norms and proposed the use of the adaptive mixed-norms as sparsity-inducing regularizers.  ... 
doi:10.1155/2014/317056 pmid:24860614 pmcid:PMC4016929 fatcat:ioaym4qnnze5bl6g7wak7777he

Mixed-norm Regularization for Brain Decoding [article]

Rémi Flamary, Ronald Phlypo
2014 arXiv   pre-print
This work investigates the use of mixed-norm regularization for sensor selection in Event-Related Potential (ERP) based Brain-Computer Interfaces (BCI).  ...  The different regularization approaches are compared on three ERP datasets showing the interest of mixed-norm regularization in terms of sensor selection.  ...  [34] by studying general mixed-norms and proposed the use of the adaptive mixed-norms as sparsity-inducing regularizers.  ... 
arXiv:1403.3628v1 fatcat:lt2hfhnugffzbobfb3i5dzp2ai

A Mixed L2 Norm Regularized HRF Estimation Method for Rapid Event-Related fMRI Experiments

Yu Lei, Li Tong, Bin Yan
2013 Computational and Mathematical Methods in Medicine  
Regularization methods have been widely used to increase the efficiency of HRF estimates. In this study, we propose a regularization framework called mixed L2 norm regularization.  ...  This framework involves Tikhonov regularization and an additional L2 norm regularization term to calculate reliable HRF estimates.  ...  Hence, we add an additional L2 regularization component into the estimation model with Tikhonov regularization, called mixed L2 norm (MN) regularization.  ... 
doi:10.1155/2013/643129 pmid:23762193 pmcid:PMC3665251 fatcat:je7xo573pnfazmszuvvukgkmpm

Sturm: Sparse Tubal-Regularized Multilinear Regression for fMRI [article]

Wenwen Li, Jian Lou, Shuo Zhou, Haiping Lu
2018 arXiv   pre-print
Specifically, the Sturm model performs multilinear regression with two regularization terms: a tubal tensor nuclear norm based on t-SVD and a standard L1 norm.  ...  We perform experiments on four classification problems, including both resting-state fMRI for disease diagnosis and task-based fMRI for neural decoding.  ...  It is commonly used for studies decoding brain cognitive states, or neural decoding. The objective is to classify (decode) the tasks performed by subjects using the fMRI information.  ... 
arXiv:1812.01496v1 fatcat:llyqce27jrdgba3j7dkk6nofgm

Finding distributed needles in neural haystacks

Christopher R. Cox, Timothy T. Rogers
2020 Journal of Neuroscience  
and whole-brain decoding with L1 or L2 regularization-each have critical and complementary blind spots under these conditions.  ...  For faces and possibly other domains, such decoding may reveal representations more widely distributed than previously suspected.  ...  As noted for simulations, this approach was unable to reveal code direction. Results for whole-brain decoding with sparse regularization are shown in the top panel of Figure 6 .  ... 
doi:10.1523/jneurosci.0904-20.2020 fatcat:jfbep6erzva65pigjdjzehnaim

Decoding the Encoding of Functional Brain Networks: an fMRI Classification Comparison of Non-negative Matrix Factorization (NMF), Independent Component Analysis (ICA), and Sparse Coding Algorithms [article]

Jianwen Xie, Pamela K. Douglas, Ying Nian Wu, Arthur L. Brody, Ariana E. Anderson
2016 arXiv   pre-print
frameworks for generating brain networks.  ...  The assumptions of independence, positivity, and sparsity to encode task-related brain networks are compared; the resulting brain networks for different constraints are used as basis functions to encode  ...  L1 Regularized Learning We can relax the L0-norm constraint over the coefficients x i by instead using a L1-norm regularization (Olshausen et al. (1996) ), which enforce x i (i = 1, ...m) to have a small  ... 
arXiv:1607.00435v1 fatcat:caxeab3hqfarxeaheqflmuy26y

A spatio-spectral approach for movement decoding from cortical and subcortical recordings in patients with Parkinson's disease [article]

Victoria Peterson, Timon Merk, Alan Bush, Vadim Nikulin, Andrea A Kühn, Wolf-Julian Neumann, Robert Mark Richardson
2021 bioRxiv   pre-print
We found that movement decoding was successful using 100 ms time windows, epoch time that is well-suited for aDBS applications.  ...  Most decoding pipelines for aDBS are based on single channel frequency domain features, neglecting spatial information available in multichannel recordings.  ...  Engemann for suggesting the use of a generalized linear model with non-negative distributions.  ... 
doi:10.1101/2021.06.06.447145 fatcat:wlfpxe4slbbofccpm5xojp6xta

Computational Methods in Neuroengineering

Chang-Hwan Im, Lei Ding, Yiwen Wang, Sung-Phil Kim
2013 Computational and Mathematical Methods in Medicine  
The paper "A mixed L2 norm regularized HRF estimation method for rapid event-related fMRI experiments" by Y.  ...  It is demonstrated that the technique significantly improves the classification accuracy in decoding brain tasks in a rapid four-category object classification experiment.  ...  In addition, we would also like to express our appreciation to the editorial board members and publishing office of the journal for their help and support throughout the preparation of this special issue  ... 
doi:10.1155/2013/617347 pmid:23935703 pmcid:PMC3713316 fatcat:r7uyvxriyncblj4taru4g75d7y

Decoding the encoding of functional brain networks: An fMRI classification comparison of non-negative matrix factorization (NMF), independent component analysis (ICA), and sparse coding algorithms

Jianwen Xie, Pamela K. Douglas, Ying Nian Wu, Arthur L. Brody, Ariana E. Anderson
2017 Journal of Neuroscience Methods  
The assumptions of independence, positivity, and sparsity to encode task-related brain networks are compared; the resulting brain networks within scan for different constraints are used as basis functions  ...  The sparse coding algorithm of L1 Regularized Learning outperformed 4 variations of ICA (p<0.001) for predicting the task being performed within each scan using artifact-cleaned components.  ...  L1 Regularized Learning We can relax the L0-norm constraint over the coefficients x i by instead using a L1-norm regularization (Olshausen et al., 1996) , which enforce x i (i = 1, .. . m) to have a small  ... 
doi:10.1016/j.jneumeth.2017.03.008 pmid:28322859 pmcid:PMC5507942 fatcat:ymwe4txaijae5iujxa2iffdawu

Bootstrapped Adaptive Threshold Selection for Statistical Model Selection and Estimation [article]

Kristofer E. Bouchard
2015 arXiv   pre-print
In part to account for such sparsity, structured regularizers are incorporated into model fitting optimization.  ...  Finally, we apply this method to the task of decoding human speech production from ECoG recordings.  ...  Furthermore, optimizing model performance is important for decoding brain signals, such as for the functioning of brain-machine interfaces.  ... 
arXiv:1505.03511v1 fatcat:zrapa2hzszeh3izl4b4dqzkkoy

A regularized discriminative framework for EEG analysis with application to brain–computer interface

Ryota Tomioka, Klaus-Robert Müller
2010 NeuroImage  
Keywords: Brain-computer interface Discriminative learning Regularization Group-lasso Spatio-temporal factorization Dual spectral norm Trace norm Convex optimization P300 speller Discriminative modeling  ...  Farquhar et al. (2006) proposed to learn all the above coefficients 11 jointly with the hinge loss and the Frobenius norm regularization for coefficients {w j } j = 1 J , {B j } j = 1 J , and {β j } j  ...  Acknowledgments This work was supported in part by grants of Japan Society for the Promotion of Science (JSPS) through the Global COE program (Computationism as a Foundation for the Sciences), Bundesministerium  ... 
doi:10.1016/j.neuroimage.2009.07.045 pmid:19646534 fatcat:tyirktmuz5de7bkejfwyb5lvey

Adaptive neural network classifier for decoding MEG signals

Ivan Zubarev, Rasmus Zetter, Hanna-Leena Halme, Lauri Parkkonen
2019 NeuroImage  
We introduce two Convolutional Neural Network (CNN) classifiers optimized for inferring brain states from magnetoencephalographic (MEG) measurements.  ...  The proposed networks outperform traditional classifiers as well as more complex neural networks when decoding evoked and induced responses to different stimuli across subjects.  ...  Today, large-scale normative data sets of functional brain data are becoming increasingly available, alleviating this problem.  ... 
doi:10.1016/j.neuroimage.2019.04.068 pmid:31059799 pmcid:PMC6609925 fatcat:orsoefql25hm7fexgqtakpki6y

Filtrage vaste marge pour l'étiquetage séquentiel à noyaux de signaux [article]

Rémi Flamary, Alain Rakotomamonjy
2010 arXiv   pre-print
We derive algorithms to solve the optimization problem and we discuss different filter regularizations for automated scaling or selection of channels.  ...  For that, we propose to jointly learn a SVM sample classifier with a temporal filtering of the channels.  ...  For that, we can use a ℓ 1 − ℓ 2 mixed-norm as a regularizer : Ω 1−2 (F ) = d v f u F 2 u,v 1 2 = d v h ||F .,v || 2 (12) Filtrage vaste marge with h(x) = x 1 2 the square root function.  ... 
arXiv:1007.0824v1 fatcat:nsgdojo4pzdebm2rwya33qhsoe

fMRI-based Decoding of Visual Information from Human Brain Activity: A Brief Review

Shuo Huang, Wei Shao, Mei-Ling Wang, Dao-Qiang Zhang
2021 International Journal of Automation and Computing  
In addition, online resources and open research problems on brain pattern analysis are also provided for the convenience of future research.  ...  In this paper, we mainly provide a comprehensive and up-to-date review of machine learning methods for analyzing neural activities with the following three aspects, i.e., brain image functional alignment  ...  [44] proposed a logistic regression-based method as well as a combination of and -norm regularizations to select discriminant brain regions across multiple conditions or groups. Grosenick et al.  ... 
doi:10.1007/s11633-020-1263-y fatcat:kwls2cvw4zgd5dti5d54uy6pgi

Decoding magnetoencephalographic rhythmic activity using spectrospatial information

Jukka-Pekka Kauppi, Lauri Parkkonen, Riitta Hari, Aapo Hyvärinen
2013 NeuroImage  
We propose a new data-driven decoding method called Spectral Linear Discriminant Analysis (Spectral LDA) for the analysis of magnetoencephalography (MEG).  ...  Furthermore, the model allows the oscillation frequencies to be different for each such state.  ...  Here, we constructed a brain decoding system for MEG with the explicit goal of providing an easily interpretable decoder, as well as a general-purpose decoding toolbox for neuroscientific research.  ... 
doi:10.1016/j.neuroimage.2013.07.026 pmid:23872494 fatcat:2f6cjzgrwbftzemfe3dgx6bvou
« Previous Showing results 1 — 15 out of 6,252 results