Marsyas  0.5.0-beta1
Public Member Functions
SMO Class Reference

Support Vector Machine classifier similar to the Weka implementation. More...

#include <SMO.h>

Inherits MarSystem.

Public Member Functions

MarSystemclone () const
void myProcess (realvec &in, realvec &out)
 Processes data.
 SMO (std::string name)
 ~SMO ()

Detailed Description

Support Vector Machine classifier similar to the Weka implementation.

Support Vector Machine Classifier similar to the Weka implementation based on the Sequential Minimum Optimization (SMO) proposed by Platt. For now only the prediction part works and only for 2-class problems. Basically the machine is represented as a linear combination of attributes that represented the separating hyperplane. Currently I use weka for training.

Definition at line 40 of file SMO.h.


Constructor & Destructor Documentation

SMO ( std::string  name)

Definition at line 25 of file SMO.cpp.

~SMO ( )

Definition at line 34 of file SMO.cpp.


Member Function Documentation

MarSystem * clone ( ) const [virtual]

Implements MarSystem.

Definition at line 40 of file SMO.cpp.

void myProcess ( realvec in,
realvec out 
) [virtual]

Processes data.

Parameters:
inInput data to read.
outOutput data to write.

Implement this method in subclass to define specific data processing.

Implements MarSystem.

Definition at line 101 of file SMO.cpp.


The documentation for this class was generated from the following files: