Sylvain Chevallier
Sylvain Chevallier
The work started in #364 introduced a `n_jobs_evaluation` in evaluation for WithinSession and CrossSession. We should do the same for CrossSubject to maintain consistency in all evaluation.
MOABB has a very good statistical methodology for experimental analysis and benchmarking algorithms. It could be a nice addition to reinforce these aspects with: - a specific example/tutorial, that details...
The Shin2017B dataset include tasks that are substraction & rest, it should not be listed in MI paradigm.
Existing CCA-based pipelines (CCA, TRCA, MsetCCA, see https://github.com/NeuroTechX/moabb/blob/79cbb71c1ed116d7e5bc9368311aff6f3e2b5f19/moabb/pipelines/classification.py#L14) need information about sampling frequency, stimulation frequencies, and/or epoch interval. This shouldn't be the case as it makes the pipelines dataset-dependant. A...
pdflatex macros defined with \newcommand{}[]{} or \renewcommand are converted by Authorea into latexml syntax : \newcommand{}[][]{}. This syntax is not supported by pdflatex and it is thus not possible to...
The first result table in documentation "The largest EEG-based Benchmark for Open Science" do not display. This PR try to correct this.
Use Epochs instead of numpy for CCA, TRCA and MsetCCA, fix label estimation.