ai.djl.nn.recurrent

Class RNN

java.lang.Object

ai.djl.nn.AbstractBlock

ai.djl.nn.ParameterBlock

ai.djl.nn.recurrent.RecurrentCell

ai.djl.nn.recurrent.RNN

All Implemented Interfaces:

Block

public class RNN
extends RecurrentCell

Applies a single-gate recurrent layer to input. Two kinds of activation function are supported: ReLU and Tanh.

Reference paper: Finding structure in time - Elman, 1988. https://crl.ucsd.edu/~elman/Papers/fsit.pdf

With ReLU activation function: \(h_t = relu(W_{ih} * x_t + b_{ih} + W_{hh} * h_{(t-1)} + b_{hh})\)

With Tanh activation function: \(h_t = \tanh(W_{ih} * x_t + b_{ih} + W_{hh} * h_{(t-1)} + b_{hh})\)

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	RNN.Activation An enum that enumerates the type of activation.
static class	RNN.Builder The Builder to construct a RNN type of Block.

Nested classes/interfaces inherited from class ai.djl.nn.recurrent.RecurrentCell

RecurrentCell.BaseBuilder<T extends RecurrentCell.BaseBuilder>

Field Summary

Fields inherited from class ai.djl.nn.recurrent.RecurrentCell

currentVersion, dropRate, gates, mode, numStackedLayers, parameters, stateOutputs, stateShape, stateSize, useBidirectional, useSequenceLength

Fields inherited from class ai.djl.nn.AbstractBlock

inputNames, inputShapes

Method Summary

Modifier and Type	Method and Description
static RNN.Builder	builder() Creates a builder to build a RNN.

Methods inherited from class ai.djl.nn.recurrent.RecurrentCell

beforeInitialize, forward, getDirectParameters, getOutputShapes, getParameterShape, loadParameters, opInputs, saveParameters, updateInputLayoutToTNC, validateInputSize

Methods inherited from class ai.djl.nn.ParameterBlock

getChildren, initialize, toString

Methods inherited from class ai.djl.nn.AbstractBlock

cast, clear, describeInput, getParameters, isInitialized, setInitializer, setInitializer

Methods inherited from class java.lang.Object

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

Methods inherited from interface ai.djl.nn.Block

forward, validateLayout

Method Detail

builder

public static RNN.Builder builder()

Creates a builder to build a RNN.

Returns:

a new builder