IDEAS home Printed from https://ideas.repec.org/a/plo/pcbi00/1007148.html
   My bibliography  Save this article

Interpreting neural decoding models using grouped model reliance

Author

Listed:
  • Simon Valentin
  • Maximilian Harkotte
  • Tzvetan Popov

Abstract

Machine learning algorithms are becoming increasingly popular for decoding psychological constructs based on neural data. However, as a step towards bridging the gap between theory-driven cognitive neuroscience and data-driven decoding approaches, there is a need for methods that allow to interpret trained decoding models. The present study demonstrates grouped model reliance as a model-agnostic permutation-based approach to this problem. Grouped model reliance indicates the extent to which a trained model relies on conceptually related groups of variables, such as frequency bands or regions of interest in electroencephalographic (EEG) data. As a case study to demonstrate the method, random forest and support vector machine models were trained on within-participant single-trial EEG data from a Sternberg working memory task. Participants were asked to memorize a sequence of digits (0–9), varying randomly in length between one, four and seven digits, where EEG recordings for working memory load estimation were taken from a 3-second retention interval. The present results confirm previous findings insofar as both random forest and support vector machine models relied on alpha-band activity in most subjects. However, as revealed by further analyses, patterns in frequency and topography varied considerably between individuals, pointing to more pronounced inter-individual differences than previously reported.Author summary: Modern machine learning algorithms currently receive considerable attention for their predictive power in neural decoding applications. However, there is a need for methods that make such predictive models interpretable. In the present work, we address the problem of assessing which aspects of the input data a trained model relies upon to make predictions. We demonstrate the use of grouped model reliance as a generally applicable method for interpreting neural decoding models. Illustrating the method on a case study, we employed an experimental design in which a comparably small number of participants (10) completed a large number of trials (972) over three electroencephalography (EEG) recording sessions from a Sternberg working memory task. Trained decoding models consistently relied on predictor variables from the alpha frequency band, which is in line with existing research on the relationship between neural oscillations and working memory. However, our analyses also indicate large inter-individual variability with respect to the relation between activity patterns and working memory load in frequency and topography. We argue that grouped model reliance provides a useful tool to better understand the workings of (sometimes otherwise black box) decoding models.

Suggested Citation

  • Simon Valentin & Maximilian Harkotte & Tzvetan Popov, 2020. "Interpreting neural decoding models using grouped model reliance," PLOS Computational Biology, Public Library of Science, vol. 16(1), pages 1-17, January.
  • Handle: RePEc:plo:pcbi00:1007148
    DOI: 10.1371/journal.pcbi.1007148
    as

    Download full text from publisher

    File URL: https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1007148
    Download Restriction: no

    File URL: https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1007148&type=printable
    Download Restriction: no

    File URL: https://libkey.io/10.1371/journal.pcbi.1007148?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Gregorutti, Baptiste & Michel, Bertrand & Saint-Pierre, Philippe, 2015. "Grouped variable importance with random forests and application to multiple functional data analysis," Computational Statistics & Data Analysis, Elsevier, vol. 90(C), pages 15-35.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Pedro Delicado & Daniel Peña, 2023. "Understanding complex predictive models with ghost variables," TEST: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 32(1), pages 107-145, March.
    2. Fabrizio Maturo & Rosanna Verde, 2023. "Supervised classification of curves via a combined use of functional data analysis and tree-based methods," Computational Statistics, Springer, vol. 38(1), pages 419-459, March.
    3. A. Poterie & J.-F. Dupuy & V. Monbet & L. Rouvière, 2019. "Classification tree algorithm for grouped variables," Computational Statistics, Springer, vol. 34(4), pages 1613-1648, December.
    4. T. Górecki & Ł. Smaga, 2017. "Multivariate analysis of variance for functional data," Journal of Applied Statistics, Taylor & Francis Journals, vol. 44(12), pages 2172-2189, September.
    5. Patrick J. Comer & Jon C. Hak & Marion S. Reid & Stephanie L. Auer & Keith A. Schulz & Healy H. Hamilton & Regan L. Smyth & Matthew M. Kling, 2019. "Habitat Climate Change Vulnerability Index Applied to Major Vegetation Types of the Western Interior United States," Land, MDPI, vol. 8(7), pages 1-27, July.
    6. Epifanio, Irene, 2016. "Functional archetype and archetypoid analysis," Computational Statistics & Data Analysis, Elsevier, vol. 104(C), pages 24-34.
    7. Pedro Delicado, 2019. "Comments on: Data science, big data and statistics," TEST: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 28(2), pages 334-337, June.
    8. Antoniadis, Anestis & Lambert-Lacroix, Sophie & Poggi, Jean-Michel, 2021. "Random forests for global sensitivity analysis: A selective review," Reliability Engineering and System Safety, Elsevier, vol. 206(C).
    9. Neska Haouij & Jean-Michel Poggi & Raja Ghozi & Sylvie Sevestre-Ghalila & Mériem Jaïdane, 2019. "Random forest-based approach for physiological functional variable selection for driver’s stress level classification," Statistical Methods & Applications, Springer;Società Italiana di Statistica, vol. 28(1), pages 157-185, March.
    10. Christophe Denis & Charlotte Dion & Miguel Martinez, 2020. "Consistent procedures for multiclass classification of discrete diffusion paths," Scandinavian Journal of Statistics, Danish Society for Theoretical Statistics;Finnish Statistical Society;Norwegian Statistical Association;Swedish Statistical Association, vol. 47(2), pages 516-554, June.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:plo:pcbi00:1007148. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: ploscompbiol (email available below). General contact details of provider: https://journals.plos.org/ploscompbiol/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.