Stephen or anyone else,

I'm getting a strange problem with nets_netmats.m

Essentially, the output of the command is a matrix full ofl NaN and I have no idea why. It looks like it's loading the data properly.

Thoughts?

Thanks,

Paul

On Mon, Jun 2, 2014 at 11:59 AM, Stephen Smith <[log in to unmask]> wrote:

Hi - this is very data (and lambda and data size) dependent - so doesn't surprise me too much....

Cheers

On 2 Jun 2014, at 16:57, Paul Beach <[log in to unmask]> wrote:

Hi FSLers,

I'm utilizing FSLnets and for some reason the nets_netmats command, in which I'm using L1-Norm regularization, is going REALLY slow (>5 min to finish) in matlab. It's been a few weeks since I last ran the scripts, but it used finish within a matter of seconds. I haven't really changed much wrt matlab or my directories of use.

Specific command is:

netmats2=nets_netmats(ts,1,'icov',10);

'ts' is a directory or two back. The L1-precision file is within the same directory as the nets_netmats file.

netmats1, which just does a regular correlation matrix, is computed immediately.

Any thoughts on how to figure out what's slowing it down? 

Cheers

--

Paul Beach
DO/PhD candidate - Year VI
Michigan State University
- College of Osteopathic Medicine
- Neuroscience Program

 - MSU Cognitive and Geriatric Neurology Team (CoGeNT)

---------------------------------------------------------------------------
Stephen M. Smith, Professor of Biomedical Engineering
Associate Director,  Oxford University FMRIB Centre

FMRIB, JR Hospital, Headington, Oxford  OX3 9DU, UK
+44 (0) 1865 222726  (fax 222717)
[log in to unmask]    http://www.fmrib.ox.ac.uk/~steve

---------------------------------------------------------------------------

Stop the cultural destruction of Tibet

--

Paul Beach
DO/PhD candidate - Year VI
Michigan State University
- College of Osteopathic Medicine
- Neuroscience Program

 - MSU Cognitive and Geriatric Neurology Team (CoGeNT)