MVPA-Light: A Classification and Regression Toolbox for Multi-Dimensional Data

Treder, Matthias S.

doi:10.3389/fnins.2020.00289

Cited by 152 publications

(203 citation statements)

References 52 publications

Supporting

Mentioning

183

Contrasting

Order By: Relevance

“…Setting the parameter to 0 enforces a zero correlation constraint whereas setting it to a positive value bounds the correlation accordingly. For MATLAB, the models have been integrated into MVPA-Light ( 31 ), an open-source machine learning toolbox. By setting the hyperparameter , ADC can be controlled in the same way as for the Python-based models.…”

Section: Methodsmentioning

confidence: 99%

Correlation Constraints for Regression Models: Controlling Bias in Brain Age Prediction

et al. 2021

Self Cite

View full text Add to dashboard Cite

In neuroimaging, the difference between chronological age and predicted brain age, also known as brain age delta, has been proposed as a pathology marker linked to a range of phenotypes. Brain age delta is estimated using regression, which involves a frequently observed bias due to a negative correlation between chronological age and brain age delta. In brain age prediction models, this correlation can manifest as an overprediction of the age of young brains and an underprediction for elderly ones. We show that this bias can be controlled for by adding correlation constraints to the model training procedure. We develop an analytical solution to this constrained optimization problem for Linear, Ridge, and Kernel Ridge regression. The solution is optimal in the least-squares sense i.e., there is no other model that satisfies the correlation constraints and has a better fit. Analyses on the PAC2019 competition data demonstrate that this approach produces optimal unbiased predictive models with a number of advantages over existing approaches. Finally, we introduce regression toolboxes for Python and MATLAB that implement our algorithm.

show abstract

Section: Methodsmentioning

confidence: 99%

Correlation Constraints for Regression Models: Controlling Bias in Brain Age Prediction

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The multivariate decoding analyses were implemented using the MVPA-Light toolbox ( Treder, 2020 ). The classifier was trained within-subject using a linear support vector machine (SVM) on the preprocessed data of the DMS task (delay phase).…”

Section: Methodsmentioning

confidence: 99%

Stress diminishes outcome but enhances response representations during instrumental learning

Staresina

Schwabe

2021

Preprint

View full text Add to dashboard Cite

Stress may shift behavioural control from a goal-directed system that encodes action-outcome relationships to a habit system that learns stimulus-response associations. Although this shift to habits is highly relevant for stress-related psychopathologies, limitations of existing behavioural paradigms hindered previous research to answer the fundamental question of whether the stress-induced bias to habits is due to impaired goal-directed or enhanced habitual processing (or both). Here, we leveraged EEG-based multivariate pattern analysis to decode neural outcome representations, crucial for goal-directed control, and response representations, essential for habitual responding, during instrumental learning. We show that stress reduces outcome representations but enhances response representations, both of which were directly associated with a behavioural index of habitual responding. Further, changes in outcome and response representations were uncorrelated, suggesting that these may reflect distinct processes. Our findings indicate that habit behaviour under stress is the result of both enhanced habitual and diminished goal-directed processing.

show abstract

“…outdoor subcategories for the scene stimuli]. LDA analysis was conducted using the MPVA light toolbox (Treder, 2020). LDA was first run on broadband amplitude to test whether the electrophysiological signal in its entirety contained stimulus-specific information.…”

Section: Linear Discriminant Analysismentioning

confidence: 99%

Alpha/beta power decreases during episodic memory formation predict the magnitude of alpha/beta power decreases during subsequent retrieval

Griffiths

Martín-Buro

Staresina

et al. 2020

Preprint

View full text Add to dashboard Cite

AbstractEpisodic memory retrieval is characterised by the vivid reinstatement of information about a personally-experienced event. Growing evidence suggests that the reinstatement of such information is supported by reductions in the spectral power of alpha/beta activity. Given that the amount of information that can be recalled depends on the amount of information that was originally encoded, information-based accounts of alpha/beta activity would suggest that retrieval-related alpha/beta power decreases similarly depend upon decreases in alpha/beta power during encoding. To test this hypothesis, seventeen human participants completed a sequence-learning task while undergoing concurrent MEG recordings. Regression-based analyses were then used to estimate how alpha/beta power decreases during encoding predicted alpha/beta power decreases during retrieval, on a trial-by-trial basis. When subjecting these parameter estimates to group-level analysis, we find evidence to suggest that retrieval-related alpha/beta (7-15Hz) power decreases fluctuate as a function of encoding-related alpha/beta power decreases. These results suggest that retrieval-related alpha/beta power decreases are contingent on the decrease in alpha/beta power that arose during encoding. Subsequent analysis uncovered no evidence to suggest that these alpha/beta power decreases reflect stimulus identity, indicating that the contingency between encoding- and retrieval-related alpha/beta power reflects the reinstatement of a neurophysiological operation, rather than neural representation, during episodic memory retrieval.

show abstract

MVPA-Light: A Classification and Regression Toolbox for Multi-Dimensional Data

Cited by 152 publications

References 52 publications

Correlation Constraints for Regression Models: Controlling Bias in Brain Age Prediction

Correlation Constraints for Regression Models: Controlling Bias in Brain Age Prediction

Stress diminishes outcome but enhances response representations during instrumental learning

Alpha/beta power decreases during episodic memory formation predict the magnitude of alpha/beta power decreases during subsequent retrieval

Contact Info

Product

Resources

About