Dear SPM,
I have recently taken a course on variational bayes with applications,
so now I want to try to use some of the concepts on my data.
Currently, I am interested in using Multivariate Autoregression as
presented in the chapter 40 of the SPM book
https://www.fil.ion.ucl.ac.uk/~wpenny/publications/spm-book/mar.pdf
1) Would you be so kind to tell me if this functionality is implemented
in SPM or a related toolbox?
2) I have attempted to read the Manual of SPM and have a look at the
extensions, but I feel somewhat overwhelmed. Could you instruct me on
how to optimally navigate these resources to determine the existence or
absence of a solver for a particular kind of problem?
3) In case I were to implement my own model that is not yet present in
SPM toolboxes, should I do it from scratch, or can I benefit from some
intermediate routines that already exist in SPM. For example, I have
considered implementing the procedure described in the above chapter
myself, but then I was wondering if there already existed a library for
KL-divergences of standard distributions (Multivariate Normal, Gamma, etc)
Best regards,
Aleksejs Fomins
|