Package io.github.kirstenali.deepj.nn

Class LSTM

java.lang.Object

io.github.kirstenali.deepj.nn.Module

io.github.kirstenali.deepj.nn.Recurrent

io.github.kirstenali.deepj.nn.LSTM

All Implemented Interfaces:

Layer, Trainable

public final class LSTM
extends Recurrent

Batch-first LSTM layer; compose layers with Sequential for stacked recurrence.

Constructor Summary

Constructors

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

Method Summary

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

cell, children, forward, run

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

LSTM

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

LSTM

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