Andrés Hoyos-Idrobo

TL;DR: T theory and experiments outline that the popular “leave‐one‐out” strategy leads to unstable and biased estimates, and a repeated random splits method should be preferred, and it can be favorable to use sane defaults, in particular for non‐sparse decoders.

TL;DR: Various two-stage strategies consisting of different initializations and nonlinear programming approaches are investigated, and these incorporate directly the strict SAR and hardware constraints, allowing the use of the proposed approach in routine.

TL;DR: This approach, fast regularized ensemble of models (FReM), includes an implicit spatial regularization by using a voxel grouping with a fast clustering algorithm that improves decoding maps stability and reduces the variance of prediction accuracy.

TL;DR: This work contributes a linear-time agglomerative clustering scheme, Recursive Nearest Agglomeration (ReNA), that approximates the data as well as traditional variance-minimizing clustering schemes that have a quadratic complexity, and shows that it can remove noise, improving subsequent analysis steps.

TL;DR: This paper designs a new framework in which the estimator is built by averaging multiple models estimated after feature clustering, to improve the conditioning of the model and shows that this combination of model averaging with spatially consistent compression can have the virtuous effect of increasing the stability of the weight maps, allowing a better interpretation of the results.