a set of C++ library classes
for neural networks development



class GradDescDecrEtaLin

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

Inheritance:


Public Methods

[more] GradDescDecrEtaLin (double x = DEFAULT_ETA, double d_fact = DEFAULT_DECR_LIN_FACTOR)
[more] ~GradDescDecrEtaLin ()
[more]void Update_param (double err, unsigned iter)

Protected Fields

[more]double decr_factor


Inherited from GradientDescent:

Public Methods

ovoid Update_delta_weights(unsigned n_layers, LayerNetTrain layer[] )
ovoid Update_weigths(unsigned n_layers, LayerNetTrain layer[])

Protected Methods

ovoid Zero_Delta_W(unsigned n_layers, LayerNetTrain layer[])


Inherited from Learning:

Public Methods

ovoid Init_rate(double val=DEFAULT_ETA)
odouble Read_rate(void)

Protected Fields

ostatic const double DEFAULT_ETA
ostatic const double DEFAULT_DECR_FACTOR
ostatic const double MIN_ETA
ostatic const double DEFAULT_DECR_LIN_FACTOR
ostatic const double DEFAULT_ALPHA
ostatic const double DEFAULT_ETA_INCR
ostatic const double DEFAULT_ETA_DECR
odouble eta


Documentation

Gradient descent learning class with linear decrement of learning rate.
It updates weights through gradient descent with linear decrement of learning rate.
odouble decr_factor

o GradDescDecrEtaLin(double x = DEFAULT_ETA, double d_fact = DEFAULT_DECR_LIN_FACTOR)

o ~GradDescDecrEtaLin()

ovoid Update_param(double err, unsigned iter)


This class has no child classes.

Alphabetic index HTML hierarchy of classes or Java


Last Updated February 2001
For comments and suggestions mail to Giorgio Valentini