model weights; interpretation; electrocorticography; SVM; Multiple Kernel Learning
Abstract :
[en] Since machine learning models have been applied to neuroimaging data, researchers have drawn conclusions from the derived weight maps. In particular, weight maps of classifiers between two conditions are often described as a proxy for the underlying signal differences between the conditions. Recent studies have however suggested that such weight maps could not reliably recover the source of the neural signals and even led to false positives (FP). In this work, we used semi-simulated data from ElectroCorticoGraphy (ECoG) to investigate how the signal-to-noise ratio and sparsity of the neural signal affect the similarity between signal and weights. We show that not all cases produce FP and that it is unlikely for FP features to have a high weight in most cases.
Disciplines :
Engineering, computing & technology: Multidisciplinary, general & others
H2020 - 654038 - DecoMP_ECoG - Decoding memory processing from experimental and spontaneous human brain activity using intracranial electrophysiological recordings and machine learning based methods.
Funders :
Marie Sklodowska Curie Actions - Horizon 2020 Wellcome Trust CE - Commission Européenne
scite shows how a scientific paper has been cited by providing the context of the citation, a classification describing whether it supports, mentions, or contrasts the cited claim, and a label indicating in which section the citation was made.
Bibliography
S. Haufe, F. Meinecke, K. Gorgen, S. Dahne, J. D. Haynes, B. Blankertz, and F. Biessmann, On the interpretation of weight vectors of linear models in multivariate neuroimaging, NeuroImage, vol. 87, 2014.
J. D. Haynes, A Primer on Pattern-Based Approaches to fMRI: Principles, Pitfalls, and Perspectives, Neuron, vol. 87, no. 2, pp. 257-270, 2015. [Online]. Available: http://dx.doi.org/10.1016/j.neuron. 2015.05.025
S. M. Kia, S. V. Pons, N. Weisz, and A. Passerini, Interpretability of multivariate brain maps in linear brain decoding: Definition, and heuristic quantification in multivariate analysis of MEG time-locked effects, Frontiers in Neuroscience, vol. 10, no. JAN, 2017.
C. Cortes and V. Vapnik, Support-Vector Networks, Machine Learning, pp. 273-297, 1995.
A. Rakotomamonjy, F. Bach, S. Canu, and Y. Grandvalet, Simple{ MKL}, Journal of Machine Learning Research, vol. 9, pp. 2491-2521, 2008.
N. Mesgarani, C. Cheung, K. Johnson, and E. F. Chang, Phonetic Feature Encoding in Human Superior Temporal Gyrus, Science, vol. 343, no. 6174, pp. 1006-1010, feb 2014. [Online]. Available: http://www.sciencemag.org/cgi/doi/10.1126/science.1245994
L. Baldassarre, M. Pontil, and J. Mouro-Miranda, Sparsity is better with stability: Combining accuracy and stability for model selection in brain decoding, Frontiers in Neuroscience, vol. 11, no. FEB, 2017.
J. Schrouff, M. Rosa, J. Rondina, A. Marquand, C. Chu, J. Ashburner, C. Phillips, J. Richiardi, and J. Mouro-Miranda, PRoNTo: Pattern recognition for neuroimaging toolbox, Neuroinformatics, vol. 11, no. 3, 2013.
J. Schrouff, J. Mouro-Miranda, C. Phillips, and J. Parvizi, Decoding intracranial EEG data with multiple kernel learning method, Journal of Neuroscience Methods, vol. 261, 2016.
J. Schrouff, J. Cremers, G. Garraux, L. Baldassarre, J. Mourao-Miranda, and C. Phillips, Localizing and comparing weight maps generated from linear kernel machine learning models, in Proceedings -2013 3rd International Workshop on Pattern Recognition in Neuroimaging, PRNI 2013, 2013.
J. Huang and T. Zhang, The benefit of group sparsity, Annals of Statistics, vol. 38, no. 4, pp. 1978-2004, 2010.
J. Schrouff, J. Monteiro, L. Portugal, M. Rosa, C. Phillips, and J. Mouro-Miranda, Embedding Anatomical or Functional Knowledge in Whole-Brain Multiple Kernel Learning Models, Neuroinformatics, 2018.
Similar publications
Sorry the service is unavailable at the moment. Please try again later.
This website uses cookies to improve user experience. Read more
Save & Close
Accept all
Decline all
Show detailsHide details
Cookie declaration
About cookies
Strictly necessary
Performance
Strictly necessary cookies allow core website functionality such as user login and account management. The website cannot be used properly without strictly necessary cookies.
This cookie is used by Cookie-Script.com service to remember visitor cookie consent preferences. It is necessary for Cookie-Script.com cookie banner to work properly.
Performance cookies are used to see how visitors use the website, eg. analytics cookies. Those cookies cannot be used to directly identify a certain visitor.
Used to store the attribution information, the referrer initially used to visit the website
Cookies are small text files that are placed on your computer by websites that you visit. Websites use cookies to help users navigate efficiently and perform certain functions. Cookies that are required for the website to operate properly are allowed to be set without your permission. All other cookies need to be approved before they can be set in the browser.
You can change your consent to cookie usage at any time on our Privacy Policy page.