On Thu, Jan 31, 2013 at 3:30 AM, Alexandre Gramfort <
[email protected]> wrote:
> > That's actually probably a very good idea. If it turns out to give good
> results in practice, we should have an option for this.
>
> +1
>
thanks guys. that's exactly what i'm trying to do now. the key is to ensure
that correspondences can be made between clusters from one execution to the
next, which often requires an additional set of info (e.g., coordinates).
but let me play around with the implementation and see how generic this can
be.
wei and olivier: thanks. the problem that this causes is in comparing
clusters from two similar datasets. are the clusters different because they
reflect different properties or simply differences in local minima.
i'll keep y'all posed.
cheers,
satra
>
>
> ------------------------------------------------------------------------------
> Everyone hates slow websites. So do we.
> Make your web apps faster with AppDynamics
> Download AppDynamics Lite for free today:
> http://p.sf.net/sfu/appdyn_d2d_jan
> _______________________________________________
> Scikit-learn-general mailing list
> [email protected]
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>
------------------------------------------------------------------------------
Everyone hates slow websites. So do we.
Make your web apps faster with AppDynamics
Download AppDynamics Lite for free today:
http://p.sf.net/sfu/appdyn_d2d_jan
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
