Declaration of the PicardIca class — Preconditioned ICA for Real Data. More...


Go to the source code of this file.
Classes | |
| class | UTILSLIB::PicardIca |
| Independent Component Analysis using the Picard algorithm. More... | |
Namespaces | |
| namespace | UTILSLIB |
| Shared utilities (I/O helpers, spectral analysis, layout management, warp algorithms). | |
Declaration of the PicardIca class — Preconditioned ICA for Real Data.
SPDX-License-Identifier: BSD-3-Clause Copyright (c) 2026 MNE-CPP Authors
Algorithm: P. Ablin, J.-F. Cardoso, A. Gramfort (2018). "Faster Independent Component Analysis by Preconditioning with Hessian Approximations." IEEE TSP 66(15):4040–4049. Uses an approximate Hessian (L-BFGS-like) preconditioner for faster convergence.
Definition in file picard_ica.h.