ensmallen
mlpack
fast, flexible C++ machine learning library
AdaBoost< WeakLearnerType, MatType > Class Template Reference

The AdaBoost class. More...

Inheritance diagram for AdaBoost< WeakLearnerType, MatType >:

Public Member Functions

 AdaBoost (const MatType &data, const arma::Row< size_t > &labels, const size_t numClasses, const WeakLearnerType &other, const size_t iterations=100, const double tolerance=1e-6)
 Constructor. More...

 
 AdaBoost (const double tolerance=1e-6)
 Create the AdaBoost object without training. More...

 
double Alpha (const size_t i) const
 Get the weights for the given weak learner. More...

 
double & Alpha (const size_t i)
 Modify the weight for the given weak learner (be careful!). More...

 
void Classify (const MatType &test, arma::Row< size_t > &predictedLabels)
 Classify the given test points. More...

 
size_t NumClasses () const
 Get the number of classes this model is trained on. More...

 
template
<
typename
Archive
>
void serialize (Archive &ar, const unsigned int)
 Serialize the AdaBoost model. More...

 
double Tolerance () const
 Get the tolerance for stopping the optimization during training. More...

 
double & Tolerance ()
 Modify the tolerance for stopping the optimization during training. More...

 
double Train (const MatType &data, const arma::Row< size_t > &labels, const size_t numClasses, const WeakLearnerType &learner, const size_t iterations=100, const double tolerance=1e-6)
 Train AdaBoost on the given dataset. More...

 
const WeakLearnerType & WeakLearner (const size_t i) const
 Get the given weak learner. More...

 
WeakLearnerType & WeakLearner (const size_t i)
 Modify the given weak learner (be careful!). More...

 
size_t WeakLearners () const
 Get the number of weak learners in the model. More...

 

Detailed Description


template<typename WeakLearnerType = mlpack::perceptron::Perceptron<>, typename MatType = arma::mat>
class mlpack::adaboost::AdaBoost< WeakLearnerType, MatType >

The AdaBoost class.

AdaBoost is a boosting algorithm, meaning that it combines an ensemble of weak learners to produce a strong learner. For more information on AdaBoost, see the following paper:

@article{schapire1999improved,
author = {Schapire, Robert E. and Singer, Yoram},
title = {Improved Boosting Algorithms Using Confidence-rated Predictions},
journal = {Machine Learning},
volume = {37},
number = {3},
month = dec,
year = {1999},
issn = {0885-6125},
pages = {297--336},
}

This class is general, and can be used with any type of weak learner, so long as the learner implements the following functions:

// A boosting constructor, which learns using the training parameters of the
// given other WeakLearner, but uses the given instance weights for training.
const MatType& data,
const arma::Row<size_t>& labels,
const arma::rowvec& weights);
// Given the test points, classify them and output predictions into
// predictedLabels.
void Classify(const MatType& data, arma::Row<size_t>& predictedLabels);

For more information on and examples of weak learners, see perceptron::Perceptron<> and decision_stump::DecisionStump<>.

Template Parameters
MatTypeData matrix type (i.e. arma::mat or arma::sp_mat).
WeakLearnerTypeType of weak learner to use.

Definition at line 81 of file adaboost.hpp.

Constructor & Destructor Documentation

◆ AdaBoost() [1/2]

AdaBoost ( const MatType &  data,
const arma::Row< size_t > &  labels,
const size_t  numClasses,
const WeakLearnerType &  other,
const size_t  iterations = 100,
const double  tolerance = 1e-6 
)

Constructor.

This runs the AdaBoost.MH algorithm to provide a trained boosting model. This constructor takes an already-initialized weak learner; all other weak learners will learn with the same parameters as the given weak learner.

Parameters
dataInput data.
labelsCorresponding labels.
iterationsNumber of boosting rounds.
tolThe tolerance for change in values of rt.
otherWeak learner that has already been initialized.

◆ AdaBoost() [2/2]

AdaBoost ( const double  tolerance = 1e-6)

Create the AdaBoost object without training.

Be sure to call Train() before calling Classify()!

Member Function Documentation

◆ Alpha() [1/2]

double Alpha ( const size_t  i) const
inline

Get the weights for the given weak learner.

Definition at line 121 of file adaboost.hpp.

◆ Alpha() [2/2]

double& Alpha ( const size_t  i)
inline

Modify the weight for the given weak learner (be careful!).

Definition at line 123 of file adaboost.hpp.

◆ Classify()

void Classify ( const MatType &  test,
arma::Row< size_t > &  predictedLabels 
)

Classify the given test points.

Parameters
testTesting data.
predictedLabelsVector in which to the predicted labels of the test set will be stored.

Referenced by AdaBoost< mlpack::perceptron::Perceptron<> >::WeakLearner().

◆ NumClasses()

size_t NumClasses ( ) const
inline

Get the number of classes this model is trained on.

Definition at line 115 of file adaboost.hpp.

◆ serialize()

void serialize ( Archive &  ar,
const unsigned  int 
)

◆ Tolerance() [1/2]

double Tolerance ( ) const
inline

Get the tolerance for stopping the optimization during training.

Definition at line 110 of file adaboost.hpp.

◆ Tolerance() [2/2]

double& Tolerance ( )
inline

Modify the tolerance for stopping the optimization during training.

Definition at line 112 of file adaboost.hpp.

◆ Train()

double Train ( const MatType &  data,
const arma::Row< size_t > &  labels,
const size_t  numClasses,
const WeakLearnerType &  learner,
const size_t  iterations = 100,
const double  tolerance = 1e-6 
)

Train AdaBoost on the given dataset.

This method takes an initialized WeakLearnerType; the parameters for this weak learner will be used to train each of the weak learners during AdaBoost training. Note that this will completely overwrite any model that has already been trained with this object.

Parameters
dataDataset to train on.
labelsLabels for each point in the dataset.
learnerLearner to use for training.
Returns
The upper bound for training error.

Referenced by AdaBoost< mlpack::perceptron::Perceptron<> >::WeakLearner().

◆ WeakLearner() [1/2]

const WeakLearnerType& WeakLearner ( const size_t  i) const
inline

Get the given weak learner.

Definition at line 126 of file adaboost.hpp.

◆ WeakLearner() [2/2]

WeakLearnerType& WeakLearner ( const size_t  i)
inline

Modify the given weak learner (be careful!).

Definition at line 128 of file adaboost.hpp.

◆ WeakLearners()

size_t WeakLearners ( ) const
inline

Get the number of weak learners in the model.

Definition at line 118 of file adaboost.hpp.


The documentation for this class was generated from the following file:
  • /home/ryan/src/mlpack.org/_src/mlpack-git/src/mlpack/methods/adaboost/adaboost.hpp