Package org.deeplearning4j.nn.layers.recurrent

Interface Summary

Interface	Description
LSTMHelper	Helper for the recurrent LSTM layer (no peephole connections).

Class Summary

Class	Description
BaseRecurrentLayer<LayerConfT extends BaseLayer>
BidirectionalLayer	Bidirectional is a "wrapper" layer: it wraps any uni-directional RNN layer to make it bidirectional. Note that multiple different modes are supported - these specify how the activations should be combined from the forward and backward RNN networks.
FwdPassReturn	Created by benny on 12/31/15.
GravesBidirectionalLSTM	RNN tutorial: http://deeplearning4j.org/usingrnns.html READ THIS FIRST Bdirectional LSTM layer implementation.
GravesLSTM	LSTM layer implementation.
LastTimeStepLayer	LastTimeStep is a "wrapper" layer: it wraps any RNN layer, and extracts out the last time step during forward pass, and returns it as a row vector (per example).
LSTM	LSTM layer implementation.
LSTMHelpers	RNN tutorial: http://deeplearning4j.org/usingrnns.html READ THIS FIRST if you want to understand what the heck is happening here.
MaskZeroLayer	Masks timesteps with 0 activation.
RnnLossLayer	Recurrent Neural Network Loss Layer. Handles calculation of gradients etc for various objective functions. NOTE: Unlike RnnOutputLayer this RnnLossLayer does not have any parameters - i.e., there is no time distributed dense component here.
RnnOutputLayer	Recurrent Neural Network Output Layer. Handles calculation of gradients etc for various objective functions. Functionally the same as OutputLayer, but handles output and label reshaping automatically. Input and output activations are same as other RNN layers: 3 dimensions with shape [miniBatchSize,nIn,timeSeriesLength] and [miniBatchSize,nOut,timeSeriesLength] respectively.
SimpleRnn	Simple RNN - aka "vanilla" RNN is the simplest type of recurrent neural network layer.