[pymvpa] Question about classifiers
debian at onerussian.com
Wed Apr 1 12:55:10 UTC 2015
On Wed, 01 Apr 2015, Serin Atiani, Dr wrote:
> To answer your questions, the data was z-scored. One of the classes is 'special' indeed, but it isn't the second one, where the large classification numbers occur in the example I sent you, and that's why it was odd. taking your advice I tried SMLR and the problem doesn't occur with it. So I guess I'll be using that, but I am not sure I know why SVD was giving me these confusion matrices.
if you could share that dataset (or portion of it) which shows such an
effect, we all could look in closer detail to get down to it. It
definitely has to do with voting, but why so consistent effect across
classes -- not sure yet. If you have problem hosting it somewhere --
email to me directly and "release" it for resharing (e.g. under
http://opendatacommons.org/licenses/pddl/ license) -- I bet there is no
subject identifying information anyhow left in it (it is functional
Yaroslav O. Halchenko, Ph.D.
http://neuro.debian.net http://www.pymvpa.org http://www.fail2ban.org
Research Scientist, Psychological and Brain Sciences Dept.
Dartmouth College, 419 Moore Hall, Hinman Box 6207, Hanover, NH 03755
Phone: +1 (603) 646-9834 Fax: +1 (603) 646-1419
More information about the Pkg-ExpPsy-PyMVPA