public class RNN extends RecurrentBlock
RNN is an implementation of recurrent neural networks which applies a single-gate
recurrent layer to input. Two kinds of activation function are supported: ReLU and Tanh.
Current implementation refers the [paper](https://crl.ucsd.edu/~elman/Papers/fsit.pdf), Finding structure in time - Elman, 1988.
The RNN operator is formulated as below:
With ReLU activation function: \(h_t = relu(W_{ih} * x_t + b_{ih} + W_{hh} * h_{(t-1)} + b_{hh})\)
With Tanh activation function: \(h_t = \tanh(W_{ih} * x_t + b_{ih} + W_{hh} * h_{(t-1)} + b_{hh})\)
| Modifier and Type | Class and Description |
|---|---|
static class |
RNN.Activation
An enum that enumerates the type of activation.
|
static class |
RNN.Builder
|
RecurrentBlock.BaseBuilder<T extends RecurrentBlock.BaseBuilder>beginState, dropRate, gates, mode, numDirections, numStackedLayers, stateOutputs, stateSize, useSequenceLengthchildren, inputNames, inputShapes, parameters, parameterShapeCallbacks, version| Modifier and Type | Method and Description |
|---|---|
static RNN.Builder |
builder()
Creates a builder to build a
RNN. |
beforeInitialize, forward, getOutputShapes, getParameterShape, isBidirectional, loadMetadata, opInputs, resetBeginStates, setBeginStates, setStateOutputs, updateInputLayoutToTNC, validateInputSizeaddChildBlock, addParameter, addParameter, addParameter, cast, clear, describeInput, getChildren, getDirectParameters, getParameters, initialize, initializeChildBlocks, isInitialized, loadParameters, readInputShapes, saveInputShapes, saveMetadata, saveParameters, setInitializer, setInitializer, toStringclone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, waitforward, forward, validateLayoutpublic static RNN.Builder builder()
RNN.