hex.deeplearning

Class Neurons.TanhDropout

java.lang.Object

hex.deeplearning.Neurons

hex.deeplearning.Neurons.Tanh

hex.deeplearning.Neurons.TanhDropout

Enclosing class:

Neurons

public static class Neurons.TanhDropout
extends Neurons.Tanh

Tanh neurons with dropout

Nested Class Summary

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

Neurons.DenseColMatrix, Neurons.DenseRowMatrix, Neurons.DenseVector, Neurons.Input, Neurons.Linear, Neurons.Matrix, Neurons.Maxout, Neurons.MaxoutDropout, Neurons.Output, Neurons.Rectifier, Neurons.RectifierDropout, Neurons.Softmax, Neurons.SparseRowMatrix, Neurons.SparseVector, Neurons.Tanh, Neurons.TanhDropout, Neurons.Vector

Field Summary

Fields inherited from class hex.deeplearning.Neurons

_a, _b, _dropout, _e, _previous, _w, DOC_FIELDS, params, units

Constructor Summary

Constructors

Constructor and Description
Neurons.TanhDropout(int units)

Method Summary

Methods

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

Methods inherited from class hex.deeplearning.Neurons.Tanh

bprop

Methods inherited from class hex.deeplearning.Neurons

init, momentum, rate, toString

Methods inherited from class java.lang.Object

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

Constructor Detail

Neurons.TanhDropout

public Neurons.TanhDropout(int units)

Method Detail

fprop

protected void fprop(long seed,
         boolean training)

Description copied from class: Neurons

Forward propagation

Overrides:

fprop in class Neurons.Tanh

Parameters:

seed - For seeding the RNG inside (for dropout)

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