[mlpack-svn] [MLPACK] #280: Kernel PCA unexpected results
MLPACK Trac
trac at coffeetalk-1.cc.gatech.edu
Fri May 10 16:05:13 EDT 2013
#280: Kernel PCA unexpected results
-------------------------------+--------------------------------------------
Reporter: marcus | Owner:
Type: defect | Status: closed
Priority: major | Milestone: mlpack 1.0.6
Component: mlpack | Resolution: fixed
Keywords: kernel pca, kpca | Blocking:
Blocked By: |
-------------------------------+--------------------------------------------
Changes (by rcurtin):
* status: new => closed
* resolution: => fixed
Comment:
r15050 should fix this. This also helps #204 towards completion. There
is a much more robust test in place now, which basically generates the
circle dataset (like you attached), then uses Kernel PCA with the Gaussian
Kernel to map it to one dimension and ensures that the three "classes" are
linearly separable.
I took your implementation and adapted it into kernel_pca_impl.hpp, so
unless you ask me to do otherwise I've added your name to the authors list
in that file and core.hpp and on the website.
Thanks again for pointing this out.
--
Ticket URL: <http://trac.research.cc.gatech.edu/fastlab/ticket/280#comment:2>
MLPACK <www.fast-lab.org>
MLPACK is an intuitive, fast, and scalable C++ machine learning library developed by the FASTLAB at Georgia Tech under Dr. Alex Gray.
More information about the mlpack-svn
mailing list