Public Member Functions

CVwNonAdaptiveLearner Class Reference


Detailed Description

VwNonAdaptiveLearner uses a standard gradient descent weight update rule.

The weight vector is updated by adding the corresponding feature multiplied by the update factor for the example.

Definition at line 30 of file VwNonAdaptiveLearner.h.

Inheritance diagram for CVwNonAdaptiveLearner:
Inheritance graph
[legend]

List of all members.

Public Member Functions

 CVwNonAdaptiveLearner ()
 CVwNonAdaptiveLearner (CVwRegressor *regressor, CVwEnvironment *vw_env)
virtual ~CVwNonAdaptiveLearner ()
virtual void train (VwExample *&ex, float32_t update)
virtual const char * get_name () const

Constructor & Destructor Documentation

Default constructor

Definition at line 20 of file VwNonAdaptiveLearner.cpp.

CVwNonAdaptiveLearner ( CVwRegressor regressor,
CVwEnvironment vw_env 
)

Constructor, initializes regressor and environment

Parameters:
regressor regressor to use
vw_env environment to use

Definition at line 25 of file VwNonAdaptiveLearner.cpp.

~CVwNonAdaptiveLearner (  )  [virtual]

Destructor

Definition at line 30 of file VwNonAdaptiveLearner.cpp.


Member Function Documentation

virtual const char* get_name ( void   )  const [virtual]

Return the name of the object

Returns:
VwNonAdaptiveLearner

Reimplemented from CVwLearner.

Definition at line 64 of file VwNonAdaptiveLearner.h.

void train ( VwExample *&  ex,
float32_t  update 
) [virtual]

Train on one example, given the update

Parameters:
ex example
update the update

Implements CVwLearner.

Definition at line 34 of file VwNonAdaptiveLearner.cpp.


The documentation for this class was generated from the following files:
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines

SHOGUN Machine Learning Toolbox - Documentation