[mlpack-svn] [MLPACK] #205: kernel usage
MLPACK Trac
trac at coffeetalk-1.cc.gatech.edu
Sat Mar 3 13:50:05 EST 2012
#205: kernel usage
----------------------+-----------------------------------------------------
Reporter: nslagle | Owner:
Type: defect | Status: new
Priority: major | Milestone: mlpack 1.0.2
Component: mlpack | Keywords: kernels, KDE, KCDE, SVM
Blocking: 199, 200 | Blocked By:
----------------------+-----------------------------------------------------
A subset of the existing kernels suffice for SVMs, kernel PCA, etc. Only
a handful, so far, are legitimate density estimation kernels. Should we
discriminate the kernels more carefully according to usage? For example,
the linear (dot product) kernel isn't appropriate for KDE and KCDE.
--
Ticket URL: <https://trac.research.cc.gatech.edu/fastlab/ticket/205>
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