Identification of nonlinear models of neural activity in bold fmri 
Daniel J. Jacobsen, Kristoffer H. Madsen, Lars Kai Hansen

Abstract  Nonlinear hemodynamic models express the BOLD signal as
a nonlinear, parametric functional of the temporal sequence of
local neural activity. Several models have been proposed for
this neural activity. We identify one such parametric model
by estimating the distribution of its parameters. These distributions
are themselves stochastic, therefore we estimate their
variance by epoch based leaveoneout cross validation, using
a MetropolisHastings algorithm for sampling of the posterior
parameter distribution. 
Keywords  BOLD fMRI, MCMC, learning, model comparison, Bayes 
Type  Conference paper [With referee] 
Conference  3rd IEEE International Symposium on Biomedical Imaging: Macro to Nano 
Year  2006 Month April pp. 952955 
ISBN / ISSN  078039576x 
BibTeX data  [bibtex] 
IMM Group(s)  Intelligent Signal Processing 