[Eeglablist] My Experiences with Rank Problem

[Arnaud Delorme]

Dear Marco,

I have changed the pop_runica function so the rank calculation would be done on double precision data in all cases.
Thanks for mentioning it,

Arno

On Jun 29, 2012, at 11:52 AM, Scott Makeig wrote:

> there was a major problem with the Matlab rank() function in some specific early versions of Matlab 7... 
> 
> in general, since ICA is an interative computation (the output of one step being the input to the next step), it should only be run at double precision.
> 
> scott makeig
> 
> On Thu, Jun 28, 2012 at 5:27 PM, Makoto Miyakoshi <mmiyakoshi at ucsd.edu> wrote:
> Dear Marco and Arno,
> 
> Thank you. This is interesting. I think this should be reported to Arno.
> 
> Makoto
> 
> 2012/6/28 Marco Montalto <montaltomarco at onvol.net>:
> > Dear Makoto,
> >
> > I would like to share my experiences regarding the issue reported lately in a post by Jan Remi. There seems to be some bug somewhere. I have a data file: on a Windows 7 PC it asks to adjust the rank from 16 to 15 (I have 16 channels) but on a MacBook Pro running OS X Lion it finds no problem with rank. The data file is exactly the same for both attempts. If I choose double precision on the PC, the problem with rank disappears.
> >
> > Regards,
> > Marco
> 
> 
> 
> --
> Makoto Miyakoshi
> JSPS Postdoctral Fellow for Research Abroad
> Swartz Center for Computational Neuroscience
> Institute for Neural Computation, University of California San Diego
> 
> _______________________________________________
> Eeglablist page: http://sccn.ucsd.edu/eeglab/eeglabmail.html
> To unsubscribe, send an empty email to eeglablist-unsubscribe at sccn.ucsd.edu
> For digest mode, send an email with the subject "set digest mime" to eeglablist-request at sccn.ucsd.edu
> 
> 
> 
> -- 
> Scott Makeig, Research Scientist and Director, Swartz Center for Computational Neuroscience, Institute for Neural Computation; Prof. of Neurosciences (Adj.), University of California San Diego, La Jolla CA 92093-0559, http://sccn.ucsd.edu/~scott
> _______________________________________________
> Eeglablist page: http://sccn.ucsd.edu/eeglab/eeglabmail.html
> To unsubscribe, send an empty email to eeglablist-unsubscribe at sccn.ucsd.edu
> For digest mode, send an email with the subject "set digest mime" to eeglablist-request at sccn.ucsd.edu

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://sccn.ucsd.edu/pipermail/eeglablist/attachments/20120629/adf930d7/attachment.html>