Manifold-regression to predict from MEG/EEG brain signals without source modeling

Authors: David Sabbagh, Pierre Ablin, Gael Varoquaux, Alexandre Gramfort, Denis A. Engemann

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We investigated the implications of these two approaches in synthetic generative models, which allowed us to control estimation bias of a linear model for prediction. We show that Wasserstein and geometric distances allow perfect out-of-sample prediction on the generative models. We then evaluated the methods on real data with regard to their effectiveness in predicting age from M/EEG covariance matrices.
Researcher Affiliation Academia Université Paris-Saclay, Inria, CEA, Palaiseau, 91120, France. Additional affiliation: Inserm, UMRS-942, Paris Diderot University, Paris, France Additional affiliation: Department of Anaesthesiology and Critical Care, Lariboisière Hospital, Assistance Publique Hôpitaux de Paris, Paris, France
Pseudocode No The paper does not contain structured pseudocode or clearly labeled algorithm blocks.
Open Source Code Yes Code used for data analysis can be found on Git Hub5.
Open Datasets Yes Finally, we apply these models to the problem of inferring age from brain data [33, 31] on 595 MEG recordings from the Cambridge Center of Aging (Cam-CAN, http://cam-can.org) covering an age range from 18 to 88 years [41].
Dataset Splits Yes We measure the score of each method as the average mean absolute error (MAE) obtained with 10-fold cross-validation.
Hardware Specification No The proposed method, including all data preprocessing, applied on the 500GB of raw MEG data from the Cam-CAN dataset, runs in approximately 12 hours on a regular desktop computer with at least 16GB of RAM.
Software Dependencies No All numerical experiments were run using the Scikit-Learn software [36], the MNE software for processing M/EEG data [21] and the Py Riemann package [13]. We also ported to Python some part of the Matlab code of Manopt toolbox [9] for computations involving Wasserstein distance.
Experiment Setup Yes We then used ridge regression and tuned its regularization parameter by generalized cross-validation [20] on a logarithmic grid of 100 values in [10 5, 103] on each training fold of a 10-fold cross-validation loop.