TanhLayer< TYPE > Class Template Reference

#include <NeuralNetwork.H>

Inheritance diagram for TanhLayer< TYPE >:

Collaboration diagram for TanhLayer< TYPE >:

Public Member Functions
	TanhLayer (int inputSize, int outputSize)
template<typename Derived >
	TanhLayer (const Eigen::MatrixBase< Derived > &weightsIn, const Eigen::MatrixBase< Derived > &biasIn)
virtual	~TanhLayer (void)
	Destructor. More...
virtual Eigen::Matrix< TYPE, Eigen::Dynamic, 1 > &	activate (const Eigen::Matrix< TYPE, Eigen::Dynamic, 1 > &input)
Public Member Functions inherited from NeuralLayer< TYPE >
	NeuralLayer (int inputSize, int outputSize)
template<typename Derived >
	NeuralLayer (const Eigen::MatrixBase< Derived > &weightsIn, const Eigen::MatrixBase< Derived > &biasIn)
virtual	~NeuralLayer (void)
	Destructor. More...
int	inputSize (void)
int	outputSize (void)

Additional Inherited Members
Public Attributes inherited from NeuralLayer< TYPE >
Eigen::Matrix< TYPE, Eigen::Dynamic, 1 >	output
	The output from this layer. More...
Protected Attributes inherited from NeuralLayer< TYPE >
Eigen::Matrix< TYPE, Eigen::Dynamic, Eigen::Dynamic >	weights
	The neural weights for this layer. More...
Eigen::Matrix< TYPE, Eigen::Dynamic, 1 >	bias
	The biases for this layer. More...

Detailed Description

template<typename TYPE>
class TanhLayer< TYPE >

Implements a neural layer with an scaled and offset tanh activation function

Template Parameters

TYPE	the precision of the data to use, e.g. float, double

Examples:

NeuralNetworkFnTest.C, and NeuralNetworkTest.C.

Definition at line 131 of file NeuralNetwork.H.

Constructor & Destructor Documentation

TanhLayer() [1/2]

template<typename TYPE >

TanhLayer< TYPE >::TanhLayer ( int  inputSize, int  outputSize  )

inline

Generate a neural layer of particular size

Parameters

inputSize	The number of the inputs
outputSize	The number of outputs

Definition at line 137 of file NeuralNetwork.H.

TanhLayer() [2/2]

template<typename TYPE >

template<typename Derived >

TanhLayer< TYPE >::TanhLayer ( const Eigen::MatrixBase< Derived > &  weightsIn, const Eigen::MatrixBase< Derived > &  biasIn  )

inline

Generate a neural layer of particular size providing the weights

Parameters

weightsIn	The weights to set
biasIn	The biases to set

Template Parameters

Derived

is used by Eigen's Curiously recurring template pattern (CRTP)

Definition at line 146 of file NeuralNetwork.H.

~TanhLayer()

template<typename TYPE >

virtual TanhLayer< TYPE >::~TanhLayer ( void  )

inlinevirtual

Destructor.

Definition at line 150 of file NeuralNetwork.H.

Member Function Documentation

activate()

template<typename TYPE >

virtual Eigen::Matrix<TYPE, Eigen::Dynamic, 1>& TanhLayer< TYPE >::activate ( const Eigen::Matrix< TYPE, Eigen::Dynamic, 1 > &  input )

inlinevirtual

The sigmoidal activation function Evaluate the neural network using the sigmoid as the activation function

Parameters

input

The input to this layer

Returns

The result of the layer after processing the input

Reimplemented from NeuralLayer< TYPE >.

Definition at line 157 of file NeuralNetwork.H.

Here is the call graph for this function:

---

The documentation for this class was generated from the following file:

• /tmp/gtkiostream/include/NeuralNetwork.H