Package io.github.kirstenali.deepj.nn

Class GRUCell

java.lang.Object

io.github.kirstenali.deepj.nn.Module

io.github.kirstenali.deepj.nn.RecurrentCell

io.github.kirstenali.deepj.nn.GRUCell

All Implemented Interfaces:

Layer, Trainable

public final class GRUCell
extends RecurrentCell

Reset-after GRU, with reset/update/candidate gate order and separate projection biases.

Field Summary

Fields inherited from class io.github.kirstenali.deepj.nn.RecurrentCell

hiddenProjection, inputProjection

Constructor Summary

Constructors

Constructor	Description
GRUCell(int inputs, int hidden, Random random)
GRUCell(int inputs, int hidden, Random random, ParameterFactory parameters)

Method Summary

Modifier and Type	Method	Description
protected RecurrentState	next(Tensor input, RecurrentState state)

Methods inherited from class io.github.kirstenali.deepj.nn.RecurrentCell

children, forward, gate, hasCellMemory, hiddenSize, initialState, inputSize, step

Methods inherited from class io.github.kirstenali.deepj.nn.Module

buffers, eval, isTraining, parameters, setTraining, train

Methods inherited from class java.lang.Object

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

Methods inherited from interface io.github.kirstenali.deepj.layers.Layer

forward, supportsIncrementalInference

Methods inherited from interface io.github.kirstenali.deepj.training.Trainable

zeroGrad

Constructor Details

GRUCell

public GRUCell(int inputs,
 int hidden,
 Random random)

GRUCell

public GRUCell(int inputs,
 int hidden,
 Random random,
 ParameterFactory parameters)

Method Details

next

protected RecurrentState next(Tensor input,
 RecurrentState state)

Specified by:

next in class RecurrentCell