Deep neural nets decode brain tasks from MEG data.
problem Classifying brain states from MEG data.
method Three deep neural network models with attention mechanisms.
result Attention mechanisms improve model generalization.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,341 papers · 148 categories
Trend · papers per month
44 results for “meg”
Extended wMEM approach for MEG inverse problem using wavelet and spatial filters.
problem Infer brain activity from full space-time data in MEG.
method Wavelet decomposition, spatial filters, Kronecker product modeling, numerical optimization.
result Smooth numerical optimization problem solved with reasonable dimensionality.
CNN outperforms traditional methods in decoding brain states from MEG signals.
problem Classifying brain states from MEG signals using traditional methods.
method Generative model-based CNN optimized for MEG brain signals.
result The CNN outperforms more complex neural networks and traditional classifiers in decoding event-related responses and oscillatory brain activity.
High temporal resolution measurements of human brain activity can be performed by recording the electric potentials on the scalp surface (electroencephalography, EEG), or by recording the magnetic fields near the surface of the head (magnetoencephalography, MEG). The analysis of the data is problematic due to the fact …
Regularizing Solutions to the MEG Inverse Problem Using Space-Time Separable Covariance Functionsstat.AP
New method regularizes MEG inverse problem for more accurate brain activity reconstruction.
problem Underdetermined inverse problem in MEG for precise brain activity reconstruction.
method Regularization using space-time separable Gaussian process model.
result Efficient and general Bayesian source reconstruction approach demonstrated.
Paper introduces MSA for weakly supervised covariance alignment in MEG signals.
problem Limited labeled signals in target datasets for MEG applications.
method Mixing model Stiefel Adaptation (MSA) leveraging unlabeled data.
result MSA outperforms recent methods in brain-age regression with MEG signals.
Novel NDL framework improves spike detection accuracy and channel localization in EEG/MEG data.
problem Manual spike identification is time-consuming and requires specialized training.
method Nested Deep Learning (NDL) framework that combines signals across all channels.
result Improves prediction accuracy and achieves better channel localization.
Probabilistic ESI model improves brain activity pattern analysis.
problem Noise sensitivity and lack of time-varying pattern flexibility in traditional ESI methods.
method Hierarchical graph prior with spanning tree constraint and alternating convex search algorithm.
result Significant improvements in source localization performance, especially at high noise levels.
New method predicts AD progression using MEG brain networks.
problem Early diagnosis and prediction of Alzheimer's disease progression.
method MG2G, a deep learning method that maps brain networks into a latent space.
result MG2G detects subtle brain connectivity patterns and predicts AD progression.
The iterative reweighted Mixed-Norm Estimate for spatio-temporal MEG/EEG source reconstructionstat.AP
New method improves brain activity analysis with better amplitude and source selection.
problem Improving brain activity analysis with high temporal and spatial resolution.
method Iterative reweighted Mixed-Norm Estimate (irMxNE) for solving non-convex optimization problems.
result Improves on standard Mixed Norm Estimate (MxNE) in amplitude bias, support recovery, and stability.
MEG models for dynamic networks estimate dependencies and shared latent space relationships.
problem Modeling dynamic networks with shared latent space relationships and dependencies.
method MEG combines mutually exciting point processes and latent space models to estimate node-specific parameters and unobserved edges.
result MEG models can estimate intensities for unobserved edges, useful for anomaly detection in real-world applications.
New method for joint MEG/EEG source imaging improves accuracy.
problem Joint MEG/EEG source imaging for group studies.
method Minimum Wasserstein Estimates (MWE) using Optimal Transport.
result MWE produces more accurate source localization than standard methods.
Model decodes sounds from neural responses, achieving 70% accuracy.
problem Decoding natural sounds from neural recordings.
method Kernel convolution model to decode acoustic features from neural responses.
result Model accurately distinguishes between sounds with 70% accuracy.
QuPWM detects epileptic spikes in MEG signals with high accuracy.
problem Manual detection of epileptic spikes in MEG signals is time-consuming and subjective.
method QuPWM combines PWM and SVM for feature extraction and classification.
result Average accuracy of 98% achieved on a balanced dataset of 3104 samples.
Unsupervised neural models predict brain activity better than supervised methods.
problem Understanding how the brain represents visual information without direct supervision.
method Built upon PredNet, used RSA to compare PredNet representations to fMRI and MEG data.
result Unsupervised models trained to predict video frames outperform supervised image classification models in predicting brain activity.
Separation of the sources and analysis of their connectivity have been an important topic in EEG/MEG analysis. To solve this problem in an automatic manner, we propose a two-layer model, in which the sources are conditionally uncorrelated from each other, but not independent; the dependence is caused by the causality i…
Efficiently implements MEG for low-rank matrix optimization problems.
problem Optimization over spectrahedron with low-rank matrices.
method Matrix Exponentiated Gradient (MEG) method with efficient implementations.
result Methods converge from a warm-start initialization with similar rates to full-SVD-based counterparts.
Improved ROCKET algorithm for brain activity classification.
problem Classifying multivariate time series data from brain activity.
method Detach-Rocket Ensemble, leveraging pruning and ensemble methods.
result Competitive classification accuracy and interpretable channel relevance.
Statistical control for spatio-temporal MEG/EEG source imaging with desparsified multi-task Lassostat.ML
New method controls false detections in brain activity localization.
problem Statistical control of false detections in brain activity localization.
method Adapted Lasso estimator for spatio-temporal MEG/EEG data.
result Offers statistical guarantees and adaptive method for thresholding.
MEG Decoding Across Subjectsstat.ML
Brain decoding is a data analysis paradigm for neuroimaging experiments that is based on predicting the stimulus presented to the subject from the concurrent brain activity. In order to make inference at the group level, a straightforward but sometimes unsuccessful approach is to train a classifier on the trials of a g…
We propose a novel technique to assess functional brain connectivity in EEG/MEG signals. Our method, called Sparsely-Connected Sources Analysis (SCSA), can overcome the problem of volume conduction by modeling neural data innovatively with the following ingredients: (a) the EEG is assumed to be a linear mixture of corr…
New method learns complex brain signal patterns from EEG/MEG data.
problem Complex waveforms in brain signals not captured by linear filters.
method Multivariate convolutional sparse coding (CSC) algorithm.
result Reveals non-sinusoidal mu-shaped patterns in brain signals.
Paper defines and quantifies interpretability of brain decoding maps.
problem Difficulty in interpreting brain maps derived from multivariate classifiers.
method Theoretical definition of interpretability, decomposition into reproducibility and representativeness, heuristic method for approximating interpretability, multi-objective criterion for model selection.
result Optimizing hyper-parameters based on proposed criterion yields more informative brain maps.
Model improves weak signal classification by sharing factors across clusters.
problem Classifying weak multi-view signals with low signal-to-noise ratio.
method Bayesian Group Factor Analysis (GFA) with shared factors across latent clusters.
result Classification accuracy significantly improved by sharing factors across clusters.
New methods predict brain age from MEG/EEG without source modeling.
problem Predicting brain age from MEG/EEG data without source localization.
method Two Riemannian approaches to vectorize rank-reduced covariance matrices for regression.
result Data-driven Riemannian methods outperform sensor-space estimators and biophysics models.
New method predicts brain activity using past states for more accurate source estimation.
problem Independent source estimates ignore temporal context of neuronal activity.
method Combines LSTM networks with Minimum-Norm Estimates (MNE) for context-dependent brain activity prediction.
result CMNE leads to more accurate source estimation compared to independent MNE.
The functional and structural representation of the brain as a complex network is marked by the fact that the comparison of noisy and intrinsically correlated high-dimensional structures between experimental conditions or groups shuns typical mass univariate methods. Furthermore most network estimation methods cannot d…
New algorithms improve CCA with stochastic approximation.
problem Efficiently compute canonical correlation analysis.
method Inexact MSG and MEG algorithms for CCA.
result Achieves ε-suboptimality in poly(1/ε) iterations.
Cross-validation in high-dimensional spaces: a lifeline for least-squares models and multi-class LDAcs.LG
A fast cross-validation method for high-dimensional data.
problem High computational cost of least-squares models in high-dimensional datasets.
method Analytical approach for k-fold cross-validation without explicit model training.
result Up to 10,000x faster than standard approach in high-dimensional data.
A new ICA model identifies shared brain activity patterns across subjects.
problem Challenges in modeling shared responses in neuroimaging studies with large cohorts.
method MultiView Independent Component Analysis (ICA) model with closed-form likelihood and alternate quasi-Newton method.
result Improved sensitivity in identifying common brain activity patterns.
A new method for multi-subject brain source imaging improves accuracy and specificity.
problem Estimating brain source locations from M/EEG data for multiple subjects.
method Sparse multi-task regression with Minimum Wasserstein Estimates and Optimal Transport metrics.
result Significant improvement in spatial specificity and localization accuracy compared to individual subject solutions.
We propose a multiresolution Gaussian process to capture long-range, non-Markovian dependencies while allowing for abrupt changes. The multiresolution GP hierarchically couples a collection of smooth GPs, each defined over an element of a random nested partition. Long-range dependencies are captured by the top-level GP…
EPSTE: A geometric token and deep learning approach to estimating transfer entropy in neuroimaging time series
problem Inferring directed interactions between neural systems from EEG and MEG
method Reframing TE estimation as a learnable problem operating on structured symbolic representations
result EPSTE achieves near-perfect recovery of ground-truth directed structure and significantly lower absolute error than the baseline
Researchers develop geodesics for a new metric on correlation matrices.
problem Lack of intrinsic tools for statistical analyses of correlation matrices.
method Developed geodesics for the quotient-affine metric on full-rank correlation matrices.
result Provided fundamental Riemannian operations for the quotient-affine metric.
GP CaKe models causal brain connectivity using Gaussian processes.
problem Understanding how one brain region drives activity in another.
method Integro-differential equations and causal kernels learned via Gaussian process regression.
result Demonstrated efficacy on simulations and MEG data.
Proposes a new Sliced-Wasserstein distance for covariance matrices in M/EEG signals.
problem Efficiently dealing with distributions of covariance matrices in M/EEG multivariate time series.
method Defines a Sliced-Wasserstein distance for symmetric positive definite matrices and applies it to brain-age prediction and Brain Computer Interface applications.
result Demonstrates computational efficiency and strong theoretical guarantees for the proposed distance.
This work improves dictionary learning speed without sacrificing accuracy.
problem Prohibitive computational cost of standard dictionary learning methods.
method Approximate dictionary learning using unrolling and gradient descent.
result Unrolling outperforms standard methods in support estimation and early iterations.
oi-VAE interprets complex data groups with nonlinear relationships.
problem Interpreting deep generative models for nonlinear group factor analysis.
method oi-VAE combines structured VAE with sparsity-inducing prior for nonlinear latent-to-observed relationships.
result oi-VAE yields meaningful interpretability in motion capture and MEG data.
The paper tackles brain decoding using high-dimensional data.
problem Classifying cognitive states from brain activity data.
method Functional principal component analysis, mutual information networks, and persistent homology.
result Features derived from these methods improve brain decoding accuracy.
This paper reviews cross-validation methods for brain decoding in neuroimaging.
problem Evaluating and tuning brain decoding models using cross-validation.
method Reviewed cross-validation procedures, including leave-one-out and repeated random splits, and discussed nested cross-validation.
result Popular leave-one-out method leads to unstable and biased estimates; repeated random splits are preferred.
Efficiently models event-based data with general parametric kernels.
problem Inference for Hawkes processes with general parametric kernels requires large datasets.
method Developed a fast gradient-based solver using a discretized version of events.
result Improved estimation of pattern latency in brain signals.
Maturation Trajectories of Cortical Resting-State Networks Depend on the Mediating Frequency Bandq-bio.NC
Beta and gamma rhythms mediate different maturation trajectories of cortical networks.
problem Understanding how distinct cortical rhythms influence network maturation.
method Magnetoencephalography (MEG) to map frequency band-specific maturation from age 7 to 29 in 162 participants.
result Beta band mediated networks follow a linear trajectory, while gamma band networks follow an asymptotic one.
AVICA estimates noise levels for better group ICA source recovery.
problem Estimating shared independent sources from multiple noisy views.
method AVICA models each view as a linear mixture of shared sources with additive noise, optimizing noise levels alongside sources.
result AVICA yields better source estimates than other methods, especially in real-world applications like MEG and fMRI.
Classification with a sparsity constraint on the solution plays a central role in many high dimensional machine learning applications. In some cases, the features can be grouped together so that entire subsets of features can be selected or not selected. In many applications, however, this can be too restrictive. In th…