paperKB
coga / coga-kb
Help
Sign in

Chunk #77 — 3 Inverse solutions — 3.1 Non parametric optimization methods — 3.1.1 The Bayesian framework — Regularization methods

Source
Review on solving the inverse problem in EEG source analysis.
Embedded
yes

Text

Another well known regularization method is the Generalized Cross Validation (GCV) method [21,25] which is based on the assumption that y is affected by normally distributed noise. The optimum alpha for GCV is that corresponding to the minimum value for the function G: