[Pkg-exppsy-pymvpa-dev] Question about new fmri_dataset

[Valentin Haenel]

Hi,

i seem to have failed to answer this one.

* Yaroslav Halchenko <debian at onerussian.com> [091229]:
> 
> On Tue, 29 Dec 2009, Valentin Haenel wrote:
> > > So, they look very close but not an exact match... how close your results
> > > matched before? may be I am taking some other results for matlab? (see path
> > > above)
> 
> > Looks like the right file
> but do you remember what differences you saw?

not sure what you mean by that.

> 
> 
> > > Although altogether I would not be too surprised since convergence
> > > tollerance was low so, no guarantee that two SVMs with noisy data would perform
> > > exactly the same ;-)
> 
> > Yeah, you could also adjust the epsilon value in your floating point comparison,
> > and see if that changes anything.
> 
> well -- I just 0-ed out all differences less than 1e-4 ... 

Yeah, that sounds about right.