On the benefits of self-taught learning for brain decoding - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles GigaScience Year : 2023

On the benefits of self-taught learning for brain decoding

Abstract

Context. We study the benefits of using a large public neuroimaging database composed of fMRI statistic maps, in a self-taught learning framework, for improving brain decoding on new tasks. First, we leverage the NeuroVault database to train, on a selection of relevant statistic maps, a convolutional autoencoder to reconstruct these maps. Then, we use this trained encoder to initialize a supervised convolutional neural network to classify tasks or cognitive processes of unseen statistic maps from large collections of the NeuroVault database. Results. We show that such a self-taught learning process always improves the performance of the classifiers but the magnitude of the benefits strongly depends on the number of samples available both for pre-training and finetuning the models and on the complexity of the targeted downstream task. Conclusion. The pre-trained model improves the classification performance and displays more generalizable features, less sensitive to individual differences.
Fichier principal
Vignette du fichier
on_the_benefits_of_self_taught_learning.pdf (3.58 Mo) Télécharger le fichier
Origin Publication funded by an institution
Licence

Dates and versions

hal-03769993 , version 1 (16-09-2022)
hal-03769993 , version 2 (21-10-2022)
hal-03769993 , version 3 (25-01-2023)
hal-03769993 , version 4 (15-02-2023)
hal-03769993 , version 5 (17-04-2023)
hal-03769993 , version 6 (03-05-2023)

Licence

Identifiers

Cite

Elodie Germani, Elisa Fromont, Camille Maumet. On the benefits of self-taught learning for brain decoding. GigaScience, 2023, 12, pp.1-17. ⟨10.1093/gigascience/giad029⟩. ⟨hal-03769993v6⟩
233 View
150 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More