Stimulus Evoked Independent Factor Analysis of MEG Data with Large Background Activity
Abstract
This paper presents a novel technique for analyzing electromagnetic imaging data obtained using the stimulus evoked experimental paradigm. The technique is based on a probabilistic graphical model, which describes the data in terms of underlying evoked and interference sources, and explicitly models the stimulus evoked paradigm. A variational Bayesian EM algorithm infers the model from data, suppresses interference sources, and reconstructs the activity of separated individual brain sources. The new algorithm outperforms existing techniques on two real datasets, as well as on simulated data.
Cite
Text
Hild et al. "Stimulus Evoked Independent Factor Analysis of MEG Data with Large Background Activity." Neural Information Processing Systems, 2005.Markdown
[Hild et al. "Stimulus Evoked Independent Factor Analysis of MEG Data with Large Background Activity." Neural Information Processing Systems, 2005.](https://mlanthology.org/neurips/2005/hild2005neurips-stimulus/)BibTeX
@inproceedings{hild2005neurips-stimulus,
title = {{Stimulus Evoked Independent Factor Analysis of MEG Data with Large Background Activity}},
author = {Hild, Kenneth and Sekihara, Kensuke and Attias, Hagai T. and Nagarajan, Srikantan S.},
booktitle = {Neural Information Processing Systems},
year = {2005},
pages = {963-970},
url = {https://mlanthology.org/neurips/2005/hild2005neurips-stimulus/}
}