SYNOPSIS

Public Member Functions

Perceptron (const MatType &data, const arma::Row< size_t > &labels, int iterations)
Constructor - constructs the perceptron by building the weightVectors matrix, which is later used in Classification.
Perceptron (const Perceptron<> &other, MatType &data, const arma::rowvec &D, const arma::Row< size_t > &labels)
Alternate constructor which copies parameters from an already initiated perceptron.
void Classify (const MatType &test, arma::Row< size_t > &predictedLabels)
Classification function.

Private Member Functions

void Train (const arma::rowvec &D)
Training Function.

Private Attributes

arma::Row< size_t > classLabels
Stores the class labels for the input data.
size_t iter
To store the number of iterations.
arma::mat trainData
Stores the training data to be used later on in UpdateWeights.
arma::mat weightVectors
Stores the weight vectors for each of the input class labels.

Detailed Description

template<typename LearnPolicy = SimpleWeightUpdate, typename WeightInitializationPolicy = ZeroInitialization, typename MatType = arma::mat>class mlpack::perceptron::Perceptron< LearnPolicy, WeightInitializationPolicy, MatType >

This class implements a simple perceptron (i.e., a single layer neural network).

It converges if the supplied training dataset is linearly separable.

Template Parameters:

LearnPolicy Options of SimpleWeightUpdate and GradientDescent.
WeightInitializationPolicy Option of ZeroInitialization and RandomInitialization.

Definition at line 46 of file perceptron.hpp.

Constructor & Destructor Documentation

template<typename LearnPolicy = SimpleWeightUpdate, typename WeightInitializationPolicy = ZeroInitialization, typename MatType = arma::mat> mlpack::perceptron::Perceptron< LearnPolicy, WeightInitializationPolicy, MatType >::Perceptron (const MatType &data, const arma::Row< size_t > &labels, intiterations)

Constructor - constructs the perceptron by building the weightVectors matrix, which is later used in Classification. It adds a bias input vector of 1 to the input data to take care of the bias weights.

Parameters:

data Input, training data.
labels Labels of dataset.
iterations Maximum number of iterations for the perceptron learning algorithm.

template<typename LearnPolicy = SimpleWeightUpdate, typename WeightInitializationPolicy = ZeroInitialization, typename MatType = arma::mat> mlpack::perceptron::Perceptron< LearnPolicy, WeightInitializationPolicy, MatType >::Perceptron (const Perceptron<> &other, MatType &data, const arma::rowvec &D, const arma::Row< size_t > &labels)

Alternate constructor which copies parameters from an already initiated perceptron.

Parameters:

other The other initiated Perceptron object from which we copy the values from.
data The data on which to train this Perceptron object on.
D Weight vector to use while training. For boosting purposes.
labels The labels of data.

Member Function Documentation

template<typename LearnPolicy = SimpleWeightUpdate, typename WeightInitializationPolicy = ZeroInitialization, typename MatType = arma::mat> void mlpack::perceptron::Perceptron< LearnPolicy, WeightInitializationPolicy, MatType >::Classify (const MatType &test, arma::Row< size_t > &predictedLabels)

Classification function. After training, use the weightVectors matrix to classify test, and put the predicted classes in predictedLabels.

Parameters:

test Testing data or data to classify.
predictedLabels Vector to store the predicted classes after classifying test.

template<typename LearnPolicy = SimpleWeightUpdate, typename WeightInitializationPolicy = ZeroInitialization, typename MatType = arma::mat> void mlpack::perceptron::Perceptron< LearnPolicy, WeightInitializationPolicy, MatType >::Train (const arma::rowvec &D) [private]

Training Function. It trains on trainData using the cost matrix D

Parameters:

D Cost matrix. Stores the cost of mispredicting instances

Member Data Documentation

template<typename LearnPolicy = SimpleWeightUpdate, typename WeightInitializationPolicy = ZeroInitialization, typename MatType = arma::mat> arma::Row<size_t> mlpack::perceptron::Perceptron< LearnPolicy, WeightInitializationPolicy, MatType >::classLabels [private]

Stores the class labels for the input data.

Definition at line 88 of file perceptron.hpp.

template<typename LearnPolicy = SimpleWeightUpdate, typename WeightInitializationPolicy = ZeroInitialization, typename MatType = arma::mat> size_t mlpack::perceptron::Perceptron< LearnPolicy, WeightInitializationPolicy, MatType >::iter [private]

To store the number of iterations.

Definition at line 85 of file perceptron.hpp.

template<typename LearnPolicy = SimpleWeightUpdate, typename WeightInitializationPolicy = ZeroInitialization, typename MatType = arma::mat> arma::mat mlpack::perceptron::Perceptron< LearnPolicy, WeightInitializationPolicy, MatType >::trainData [private]

Stores the training data to be used later on in UpdateWeights.

Definition at line 94 of file perceptron.hpp.

template<typename LearnPolicy = SimpleWeightUpdate, typename WeightInitializationPolicy = ZeroInitialization, typename MatType = arma::mat> arma::mat mlpack::perceptron::Perceptron< LearnPolicy, WeightInitializationPolicy, MatType >::weightVectors [private]

Stores the weight vectors for each of the input class labels.

Definition at line 91 of file perceptron.hpp.

Author

Generated automatically by Doxygen for MLPACK from the source code.