[mlpack-svn] [MLPACK] #163: Decide on "basic type" of observation for MLPACK

MLPACK Trac trac at coffeetalk-1.cc.gatech.edu
Wed Nov 23 13:35:19 EST 2011


#163: Decide on "basic type" of observation for MLPACK
--------------------------------------+-------------------------------------
  Reporter:  rcurtin                  |        Owner:            
      Type:  wishlist                 |       Status:  new       
  Priority:  blocker                  |    Milestone:  MLPACK 1.0
 Component:  MLPACK                   |   Resolution:            
  Keywords:  mlpack observation type  |     Blocking:  132       
Blocked By:                           |  
--------------------------------------+-------------------------------------

Comment (by nslagle):

 That being the case, let the machine learning technique decide whether it
 prefers arma::vec or arma::Col<size_t>.  Utility calls might require an
 additional layer of templating (pass arma::Col<T> instead of arma::vec).

 One potential drawback in requiring an observation to be a vector of some
 type is that we cannot specify an observation of mixed types as with a
 structure.  That is, some features might be booleans, some might be
 integers, some might be strings, etc.  I suppose we might send
 arma::Col<struct myMLObservationType> into the technique, provided
 Armadillo can handle this.

-- 
Ticket URL: <http://trac.research.cc.gatech.edu/fastlab/ticket/163#comment:5>
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