Recurrent..::..RNN Method

Recurrent neural network defined with activation function

Namespace:  SiaNet.NN
Assembly:  SiaNet (in SiaNet.dll)

Syntax


public static Function RNN(
	int inputDim,
	uint hiddenSize,
	uint numLayers,
	string activation,
	bool bidirectional,
	string weightInitializer
)
Public Shared Function RNN ( _
	inputDim As Integer, _
	hiddenSize As UInteger, _
	numLayers As UInteger, _
	activation As String, _
	bidirectional As Boolean, _
	weightInitializer As String _
) As Function
public:
static Function^ RNN(
	int^ inputDim, 
	unsigned int^ hiddenSize, 
	unsigned int^ numLayers, 
	String^ activation, 
	bool^ bidirectional, 
	String^ weightInitializer
)

Parameters

inputDim
Type: Int32
The input dim.
hiddenSize
Type: UInt32
Size of the hidden.
numLayers
Type: UInt32
The number layers.
activation
Type: String
Activation function to use. Supported are ReLU and TanH OptActivations.
bidirectional
Type: Boolean
If bidirectional RNN
weightInitializer
Type: String
The weight initializer.

Return Value

Exceptions


ExceptionCondition
ExceptionSupported activation for RNN is ReLU and Tanh