hex.deeplearning

Class Neurons.RectifierDropout

java.lang.Object

hex.deeplearning.Neurons

hex.deeplearning.Neurons.Rectifier

hex.deeplearning.Neurons.RectifierDropout

Enclosing class:

Neurons

public static class Neurons.RectifierDropout
extends Neurons.Rectifier

Rectifier linear unit (ReLU) neurons with dropout

Nested Class Summary

Nested classes/interfaces inherited from class hex.deeplearning.Neurons

Neurons.ExpRectifier, Neurons.ExpRectifierDropout, Neurons.Input, Neurons.Linear, Neurons.Maxout, Neurons.MaxoutDropout, Neurons.Output, Neurons.Rectifier, Neurons.RectifierDropout, Neurons.Softmax, Neurons.Tanh, Neurons.TanhDropout

Field Summary

Fields inherited from class hex.deeplearning.Neurons

_a, _avg_a, _b, _bEA, _dropout, _e, _index, _input, _origa, _previous, _w, _wEA, params, units

Constructor Summary

Constructors

Constructor and Description
RectifierDropout(int units)

Method Summary

Modifier and Type	Method and Description
protected void	fprop(long seed, boolean training, int n) Forward propagation

Methods inherited from class hex.deeplearning.Neurons.Rectifier

bprop

Methods inherited from class hex.deeplearning.Neurons

autoEncoderGradient, bpropOutputLayer, init, momentum, momentum, rate, setOutputLayerGradient, toString

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Detail

RectifierDropout

public RectifierDropout(int units)

Method Detail

fprop

protected void fprop(long seed,
                     boolean training,
                     int n)

Description copied from class: Neurons

Forward propagation

Overrides:

fprop in class Neurons.Rectifier

Parameters:

seed - For seeding the RNG inside (for dropout)

training - Whether training is done or just testing (no need for dropout)

n - number of actually trained samples in this mini-batch