[mlpack-svn] [MLPACK] #166: PCA fails comparison with MATLAB

[MLPACK Trac]

#166: PCA fails comparison with MATLAB
------------------------------------------------------------+---------------
  Reporter:  rcurtin                                        |        Owner:  ajinkya   
      Type:  defect                                         |       Status:  new       
  Priority:  critical                                       |    Milestone:  MLPACK 1.0
 Component:  MLPACK                                         |   Resolution:            
  Keywords:  pca incorrect dimensionality reduction matlab  |     Blocking:  126       
Blocked By:                                                 |  
------------------------------------------------------------+---------------

Comment (by ajinkya):

 By default other packages for princomp (atleast R and Armadillo princomp)
 do not do mean-centering and scaling (with standard deviation). So if we
 want to provide that we will have to add that as a parameter to make this
 consistent with those packages.
 Based on that decision I modify the api and also refactor the code
 duplication in Apply().

-- 
Ticket URL: <http://trac.research.cc.gatech.edu/fastlab/ticket/166#comment:1>
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.