hex.nn

Class Neurons.Maxout

java.lang.Object

hex.nn.Neurons

hex.nn.Neurons.Maxout

Direct Known Subclasses:

Neurons.MaxoutDropout

Enclosing class:

Neurons

public static class Neurons.Maxout
extends Neurons

Nested Class Summary

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

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.nn.Neurons

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

Constructor Summary

Constructors

Constructor and Description
Neurons.Maxout(int units)

Method Summary

Methods

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

Methods inherited from class hex.nn.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.Maxout

public Neurons.Maxout(int units)

Method Detail

fprop

protected void fprop(long seed,
         boolean training)

Description copied from class: Neurons

Forward propagation

Specified by:

fprop in class Neurons

Parameters:

seed - For seeding the RNG inside (for dropout)

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

bprop

protected void bprop()

Description copied from class: Neurons

Back propagation

Specified by:

bprop in class Neurons