[pymvpa] Regression estimates?

[Francisco Pereira]

I'd start with what Yarik suggested (using the SVD trick of
decomposing XX' rather than X when X is a very wide matrix), if I knew
nothing else about the structure of the features. What can you tell us
about that?..

cheers,
Francisco

On Thu, Mar 31, 2011 at 8:32 AM, Yaroslav Halchenko
<debian at onerussian.com> wrote:
> hold on there -- there was fresh release... I will make it available
> from neuro.debian later on today
>
> On Thu, 31 Mar 2011, Per B. Sederberg wrote:
>
>> Ahhhhh, I've been bitten by the convolution_nodes bug in mdp!  So no
>> easy ICA for me without installing mdp from source (or some other
>> drastic measure)...
>
> --
> =------------------------------------------------------------------=
> Keep in touch                                     www.onerussian.com
> Yaroslav Halchenko                 www.ohloh.net/accounts/yarikoptic
>
> _______________________________________________
> Pkg-ExpPsy-PyMVPA mailing list
> Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org
> http://lists.alioth.debian.org/mailman/listinfo/pkg-exppsy-pymvpa
>