gpmp::ml::MDLAutoEncoder Class Reference

MDLAutoEncoder Minimal Description Length class, a derived class from AutoEncoder. More...

#include <encoder.hpp>

Inheritance diagram for gpmp::ml::MDLAutoEncoder:

Public Member Functions
	MDLAutoEncoder (int input_size, int hidden_size, int output_size, double learning_rate, double mdl_weight)
	Constructor for the MDLAutoEncoder class. More...
virtual void	train (const std::vector< std::vector< double >> &training_data, int epochs) override
	Trains the MDL autoencoder on the given training data. More...
Public Member Functions inherited from gpmp::ml::AutoEncoder
	AutoEncoder (int input_size, int hidden_size, int output_size, double learning_rate)
	Constructor for the AutoEncoder class. More...
std::vector< double >	sigmoid (const std::vector< double > &x)
	Sigmoid activation function. More...
std::vector< double >	forward (const std::vector< double > &input)
	Forward pass through the autoencoder. More...
void	lrate_set (double initial_rate)
	Set the initial learning rate. More...
virtual void	lrate_update (int epoch)
	Update the learning rate based on a schedule. More...
void	display ()
	Print the weights of the autoencoder. More...
virtual void	save (const std::string &filename) const
	Save the model weights to a file. More...
virtual void	load (const std::string &filename)
	Load model weights from a file. More...

Public Attributes
double	mdl_weight
	Weight for the MDL penalty term. More...
Public Attributes inherited from gpmp::ml::AutoEncoder
int	input_size
	Size of the input layer. More...
int	hidden_size
	Size of the hidden layer. More...
int	output_size
	Size of the output layer. More...
double	learning_rate
	Learning rate for training the autoencoder. More...
std::vector< std::vector< double > >	weights_input_hidden
	Weights from the input layer to the hidden layer. More...
std::vector< std::vector< double > >	weights_hidden_output
	Weights from the hidden layer to the output layer. More...

Detailed Description

MDLAutoEncoder Minimal Description Length class, a derived class from AutoEncoder.

Definition at line 314 of file encoder.hpp.

Constructor & Destructor Documentation

MDLAutoEncoder()

gpmp::ml::MDLAutoEncoder::MDLAutoEncoder	(	int	input_size,
		int	hidden_size,
		int	output_size,
		double	learning_rate,
		double	mdl_weight
	)

Constructor for the MDLAutoEncoder class.

Parameters

input_size	The size of the input layer
hidden_size	The size of the hidden layer
output_size	The size of the output layer
learning_rate	The learning rate for training
mdl_weight	The weight for the MDL penalty term

Definition at line 378 of file encoder.cpp.

    : AutoEncoder(in_size, h_size, out_size, l_rate), mdl_weight(m_wt) {
}

Member Function Documentation

train()

void gpmp::ml::MDLAutoEncoder::train ( const std::vector< std::vector< double >> &  training_data, int  epochs  )

overridevirtual

Trains the MDL autoencoder on the given training data.

Overrides the train method in the base class with MDL penalty

Parameters

training_data	The training data
epochs	The number of training epochs

Reimplemented from gpmp::ml::AutoEncoder.

Definition at line 386 of file encoder.cpp.

                {
    for (int epoch = 0; epoch < epochs; ++epoch) {
        for (const auto &input : training_data) {
            // forward pass
            std::vector<double> hidden = forward(input);
 
            // backward pass (gradient descent)
            for (int i = 0; i < output_size; ++i) {
                for (int j = 0; j < hidden_size; ++j) {
                    weights_hidden_output[j][i] -=
                        learning_rate * (hidden[i] - input[i]) * hidden[j];
                }
            }
 
            for (int i = 0; i < hidden_size; ++i) {
                for (int j = 0; j < input_size; ++j) {
                    double error = 0;
                    for (int k = 0; k < output_size; ++k) {
                        error += (hidden[k] - input[k]) *
                                 weights_hidden_output[i][k];
                    }
                    double mdl_term = mdl_weight * log(1.0 + fabs(error));
                    weights_input_hidden[j][i] -=
                        learning_rate * (error + mdl_term) * input[j] *
                        (1 - hidden[i]) * hidden[i];
                }
            }
        }
    }
}

Member Data Documentation

mdl_weight

double gpmp::ml::MDLAutoEncoder::mdl_weight

Weight for the MDL penalty term.

Definition at line 319 of file encoder.hpp.

---

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

• include/openGPMP/ml/encoder.hpp
• modules/ml/encoder.cpp