GTK+ IOStream  Beta
<< GTK+ >> add C++ IOStream operators to GTK+. Now with extra abilities ... like network serialisation
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Pages
Public Member Functions | List of all members
SigmoidLayer< TYPE > Class Template Reference

#include <NeuralNetwork.H>

Inheritance diagram for SigmoidLayer< TYPE >:
Inheritance graph
[legend]
Collaboration diagram for SigmoidLayer< TYPE >:
Collaboration graph
[legend]

Public Member Functions

 SigmoidLayer (int inputSize, int outputSize)
 
template<typename Derived >
 SigmoidLayer (const Eigen::MatrixBase< Derived > &weightsIn, const Eigen::MatrixBase< Derived > &biasIn)
 
virtual ~SigmoidLayer (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...
 

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 SigmoidLayer< TYPE >

Implements a neural layer with a sigmoid activation function
Template Parameters
TYPEthe precision of the data to use, e.g. float, double

Definition at line 81 of file NeuralNetwork.H.

Constructor & Destructor Documentation

template<typename TYPE >
SigmoidLayer< TYPE >::SigmoidLayer ( int  inputSize,
int  outputSize 
)
inline
Generate a neural layer of particular size
Parameters
inputSizeThe number of the inputs
outputSizeThe number of outputs

Definition at line 87 of file NeuralNetwork.H.

template<typename TYPE >
template<typename Derived >
SigmoidLayer< TYPE >::SigmoidLayer ( const Eigen::MatrixBase< Derived > &  weightsIn,
const Eigen::MatrixBase< Derived > &  biasIn 
)
inline
Generate a neural layer of particular size providing the weights
Parameters
weightsInThe weights to set
biasInThe biases to set
Template Parameters
Derivedis used by Eigen's Curiously recurring template pattern (CRTP)

Definition at line 96 of file NeuralNetwork.H.

template<typename TYPE >
virtual SigmoidLayer< TYPE >::~SigmoidLayer ( void  )
inlinevirtual

Destructor.

Definition at line 100 of file NeuralNetwork.H.

Member Function Documentation

template<typename TYPE >
virtual Eigen::Matrix<TYPE, Eigen::Dynamic, 1>& SigmoidLayer< TYPE >::activate ( const Eigen::Matrix< TYPE, Eigen::Dynamic, 1 > &  input)
inlinevirtual
The sigmoidal activation function

Evaluate the neural layer using the sigmoid as the activation function

Parameters
inputThe input to this layer
Returns
The result of the layer after processing the input

Reimplemented from NeuralLayer< TYPE >.

Definition at line 107 of file NeuralNetwork.H.

Here is the call graph for this function:


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