Gradient descent with exponential decrement of learning rate - HTML documentaiton under construction.

Inheritance:

Public Methods

	GradDescDecrEtaExp (double x = DEFAULT_ETA, double d_fact = DEFAULT_DECR_FACTOR)
	~GradDescDecrEtaExp ()
void	Update_param (double err, unsigned iter)

Protected Fields

double

decr_factor

Inherited from GradientDescent:

Public Methods

void Update_delta_weights(unsigned n_layers, LayerNetTrain layer[] )

void Update_weigths(unsigned n_layers, LayerNetTrain layer[])

Protected Methods

void Zero_Delta_W(unsigned n_layers, LayerNetTrain layer[])

Inherited from Learning:

Public Methods

void Init_rate(double val=DEFAULT_ETA)

double Read_rate(void)

Protected Fields

static const double DEFAULT_ETA

static const double DEFAULT_DECR_FACTOR

static const double MIN_ETA

static const double DEFAULT_DECR_LIN_FACTOR

static const double DEFAULT_ALPHA

static const double DEFAULT_ETA_INCR

static const double DEFAULT_ETA_DECR

double eta

Documentation

Gradient descent learning class with exponential decrement of learning rate.
It updates weights through gradient descent with exponential decrement of learning rate.

double decr_factor

GradDescDecrEtaExp(double x = DEFAULT_ETA, double d_fact = DEFAULT_DECR_FACTOR)

~GradDescDecrEtaExp()

void Update_param(double err, unsigned iter)

This class has no child classes.

Alphabetic index HTML hierarchy of classes or Java