FastICA is made robust to unknown source distributions by learning the required nonlinear function from the empirical characteristic function of the mixtures.
A new learning algorithm for blind signal separation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
ICA-based artifact removal does not consistently improve deep network decoding performance on EEG data across three BCI tasks and multiple models.
citing papers explorer
-
FastICA with Learned Scores from the Empirical Characteristic Function
FastICA is made robust to unknown source distributions by learning the required nonlinear function from the empirical characteristic function of the mixtures.
-
I see artifacts: ICA-based EEG artifact removal does not improve deep network decoding across three BCI tasks
ICA-based artifact removal does not consistently improve deep network decoding performance on EEG data across three BCI tasks and multiple models.