Filters








396 Hits in 6.8 sec

Assessing and tuning brain decoders: Cross-validation, caveats, and guidelines

Gaël Varoquaux, Pradeep Reddy Raamana, Denis A. Engemann, Andrés Hoyos-Idrobo, Yannick Schwartz, Bertrand Thirion
2017 NeuroImage  
Such evaluation is achieved via cross-validation, a method also used to tune decoders' hyper-parameters. This paper is a review on cross-validation procedures for decoding in neuroimaging.  ...  Nested cross-validation can tune decoders' parameters while avoiding circularity bias. However we find that it can be more favorable to use sane defaults, in particular for non-sparse decoders.  ...  Results: cross-validation to assess predictive power Reliability of the cross-validation measure.  ... 
doi:10.1016/j.neuroimage.2016.10.038 pmid:27989847 fatcat:ffbhhxp37vfhdohas3rd66ttom

Eye Movement-Related Confounds in Neural Decoding of Visual Working Memory Representations

Pim Mostert, Anke Marit Albers, Loek Brinkman, Larisa Todorova, Peter Kok, Floris P. de Lange
2018 eNeuro  
However, with its promises also come potential caveats.  ...  Significance Statement Neural decoding is an important and relatively novel technique that has opened up new avenues for cognitive neuroscience research.  ...  To test whether we could decode stimulus identity from the MEG signal, we applied the classifier to the same (pooled) data using cross-validation and found successful decoding during a period of up to  ... 
doi:10.1523/eneuro.0401-17.2018 pmid:30310862 pmcid:PMC6179574 fatcat:23h73x3kqfag5pq7pi7vsrvtta

Using Coherence-based spectro-spatial filters for stimulus features prediction from electro-corticographic recordings

Jaime Delgado Saa, Andy Christen, Stephanie Martin, Brian N. Pasley, Robert T. Knight, Anne-Lise Giraud
2020 Scientific Reports  
and brain responses manually.  ...  In decoding tasks, on the contrary, brain responses are used to predict the stimuli, and traditionally, the signals are assumed stationary within trials, which is rarely the case for natural stimuli.  ...  Acknowledgements This work was performed thanks for the Swiss National Funds project grant to ALG 320030_163040, and to the EU FET-BrainCom project and NINDS R3723115. The authors thanks Dr.  ... 
doi:10.1038/s41598-020-63303-1 pmid:32376909 pmcid:PMC7203138 fatcat:rajl3wh6vbbhrjz346rmcq6qpm

Thought-based interaction: Same data, same methods, different results?

Reinhold Scherer
2019 PLoS Biology  
What is the best practice to ensure that results are stringent and conclusive and analyses replicable?  ...  However, the validity of the evidence has been questioned: independent reanalysis of the same data yielded significantly different results.  ...  Exceeding chance level by chance: The caveat of theoretical chance levels in brain signal classification and statistical assessment of decoding accuracy.  ... 
doi:10.1371/journal.pbio.3000190 pmid:30958813 pmcid:PMC6453358 fatcat:qw6nun7w5zagxpylzbfdrqt5y4

Classification Accuracy of Neuroimaging Biomarkers in Attention-Deficit/Hyperactivity Disorder: Effects of Sample Size and Circular Analysis

Alfredo A. Pulini, Wesley T. Kerr, Sandra K. Loo, Agatha Lenartowicz
2018 Biological Psychiatry: Cognitive Neuroscience and Neuroimaging  
Motivated by an inconsistency between reports of high diagnosis-classification accuracies and known heterogeneity in attention-deficit/hyperactivity disorder (ADHD), this study assessed classification  ...  Varoquaux G, Raamana PR, Engemann DA, Hoyos-Idrobo A, Schwartz Y, Thirion B (2017): Assessing and tuning brain decoders: Cross-validation, caveats, and guidelines. Neuroimage. 145:166-179.  ...  Combrisson E, Jerbi K (2015): Exceeding chance level by chance: The caveat of theoretical chance levels in brain signal classification and statistical assessment of decoding accuracy.  ... 
doi:10.1016/j.bpsc.2018.06.003 pmid:30064848 pmcid:PMC6310118 fatcat:thwebnsgkzfyhfpenk7ou7bsju

Population Coding in an Innately Relevant Olfactory Area

Giuliano Iurilli, Sandeep Robert Datta
2017 Neuron  
tuning, reliability and correlation structure.  ...  These results demonstrate that brain regions mediating odordriven innate behaviors can, like brain areas involved in odor learning, represent odor objects using distributive population codes; these findings  ...  SRD is supported by fellowships from the Burroughs Wellcome Fund, the Vallee Foundation, the Khodadad Program, by grant RO11DC011558 from the National Institutes of Health, and by the Global Brain Initiative  ... 
doi:10.1016/j.neuron.2017.02.010 pmid:28238549 pmcid:PMC5370575 fatcat:jph7xswhrjejddgn2os22hklgq

MEG/EEG group study with MNE: recommendations, quality assessments and best practices [article]

Mainak Jas, Eric Larson, Denis-Alexander Engemann, Jaakko Leppakangas, Samu Taulu, Matti Hamalainen, Alexandre Gramfort
2017 bioRxiv   pre-print
The analysis covers preprocessing steps, quality assurance steps, sensor space analysis of evoked responses, source localization, and statistics in both sensor and source space.  ...  inverse versus LCMV beamformer, and the use of univariate or multivariate statistics.  ...  Acknowledgement We would like to thank the many members of the MNE community who have contributed through code, comments, and even complaints, to the improvement and design of this software.  ... 
doi:10.1101/240044 fatcat:cgw6ubvyqrgxvnq2dmwechcx6m

A Reproducible MEG/EEG Group Study With the MNE Software: Recommendations, Quality Assessments, and Good Practices

Mainak Jas, Eric Larson, Denis A. Engemann, Jaakko Leppäkangas, Samu Taulu, Matti Hämäläinen, Alexandre Gramfort
2018 Frontiers in Neuroscience  
LCMV beamformer, and the use of univariate or multivariate statistics.  ...  The analysis covers preprocessing steps, quality assurance steps, sensor space analysis of evoked responses, source localization, and statistics in both sensor and source space.  ...  ST and MH interpreted the data, participated in the scientific discussions, and provided critical insights. All authors reviewed the manuscript and approved it for publication.  ... 
doi:10.3389/fnins.2018.00530 pmid:30127712 pmcid:PMC6088222 fatcat:22t3ir7eznbohknhi2tgo42ywm

Audiovisual Modulation in Mouse Primary Visual Cortex Depends on Cross-Modal Stimulus Configuration and Congruency

Guido T. Meijer, Jorrit S. Montijn, Cyriel M.A. Pennartz, Carien S. Lansink
2017 Journal of Neuroscience  
Using two-photon imaging of large groups of neurons, we show that multisensory modulation of V1 populations is strongly determined by the individual and shared features of cross-modal stimulus constituents  ...  stimuli, and their prevalence was balanced.  ...  A leave-one-out cross-validation procedure was used in which the to-bedecoded trial was excluded from the training set when determining the likelihood functions.  ... 
doi:10.1523/jneurosci.0468-17.2017 pmid:28821672 fatcat:7wxkpnmnrrcw5ax3eoso52ukzy

Population coding in mouse visual cortex: response reliability and dissociability of stimulus tuning and noise correlation

Jorrit S. Montijn, Martin Vinck, Cyriel M. A. Pennartz
2014 Frontiers in Computational Neuroscience  
We show that the variability of neuronal responses may hamper the decoding of population activity, and that a normalization to correct for this variability may be of critical importance for correct decoding  ...  Second, by comparing noise correlations and stimulus tuning we find that these properties have dissociated anatomical correlates, even though noise correlations have been previously hypothesized to reflect  ...  ACKNOWLEDGMENTS This work was supported by the Netherlands Organization for Scientific Research-Excellence grant for the Brain & Cognition project 433-09-208 and the EU FP7-ICT grant 270108.  ... 
doi:10.3389/fncom.2014.00058 pmid:24917812 pmcid:PMC4040453 fatcat:lkltcwch55akrjxhyexi5mfot4

Simple Acoustic Features Can Explain Phoneme-Based Predictions of Cortical Responses to Speech

Christoph Daube, Robin A.A. Ince, Joachim Gross
2019 Current Biology  
We find that two recent results, the improved performance of an encoding model in which annotated linguistic and acoustic features were combined and the decoding of phoneme subgroups from phoneme-locked  ...  By replicating our results in publicly available electroencephalography (EEG) data, we conclude that models of brain responses based on linguistic features can serve as excellent benchmarks.  ...  Assessing and tuning brain decoders: cross-validation, caveats, and guidelines. Neuroimage 145 (Pt B), 166-179. 45. Acerbi, L., and Ma, W.J. (2017).  ... 
doi:10.1016/j.cub.2019.04.067 pmid:31130454 pmcid:PMC6584359 fatcat:ub46l7mij5civae2ugot6hxhzi

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

Matthias S. Treder
2020 Frontiers in Neuroscience  
., time x time) and searchlight analysis. The toolbox performs cross-validation, hyperparameter tuning, and nested preprocessing.  ...  It computes various classification and regression metrics and establishes their statistical significance, is modular and easily extendable.  ...  ., and Thirion, B. (2017). Assessing and tuning brain decoders: cross-validation, caveats, and guidelines.  ... 
doi:10.3389/fnins.2020.00289 pmid:32581662 pmcid:PMC7287158 fatcat:7mxsgmesynayjk5q34jehmm5j4

Comparing Task-Relevant Information Across Different Methods of Extracting Functional Connectivity [article]

Sophie Benitez Stulz, Andrea Insabato, Gustavo Deco, Matthieu Gilson, Mario Senden
2018 bioRxiv   pre-print
between-subject cross-validation, which aims at extracting signatures that generalize across subjects.  ...  The measures are evaluated in their ability to discriminate the five tasks with two types of crossvalidation: within-subject cross-validation, which reflects the stability of the signature over time; and  ...  Acknowledgements This research was funded by the European Union's Horizon 2020 Research and Innovation Programme under Grant Agreements No. 7202070 (HBP SGA1) and 737691 (HBP SGA2).  ... 
doi:10.1101/509059 fatcat:cjlghfavyze4vdz5sfmcxxtljy

Classical Statistics and Statistical Learning in Imaging Neuroscience

Danilo Bzdok
2017 Frontiers in Neuroscience  
Throughout recent years, statistical learning methods enjoy increasing popularity especially for applications in rich and complex data, including cross-validated out-of-sample prediction using pattern  ...  Brain-imaging research has predominantly generated insight by means of classical statistics, including regression-type analyses and null-hypothesis testing using t-test and ANOVA.  ...  Assessing generalization performance of different sparse models using 5fold cross-validation yields the non-zero coefficients for few brain voxels whose volumetric information is most predictive of an  ... 
doi:10.3389/fnins.2017.00543 pmid:29056896 pmcid:PMC5635056 fatcat:ilwuesppwzelphg6rjrpj6b4ri

OUP accepted manuscript

2018 Cerebral Cortex  
These findings suggest that characteristic tuning of human auditory cortex to slow temporal modulations is unique and may have emerged as a critical step in the evolution of speech and language.  ...  Conversely, we observed a striking interspecies difference in cortical sensitivity to temporal modulations: While decoding from macaque auditory cortex was most accurate at fast rates ( > 30 Hz), humans  ...  Notes We thank Vittoria de Angelis, Giancarlo Valente and Michelle Moerel for useful discussions on data analysis. We thank three anonymous reviewers for their valuable comments.  ... 
doi:10.1093/cercor/bhy243 pmid:30395192 fatcat:eadsfyg4zba5zlm5ir3mgaejym
« Previous Showing results 1 — 15 out of 396 results