GTK+ IOStream
Beta
<< GTK+ >> add C++ IOStream operators to GTK+. Now with extra abilities ... like network serialisation
|
#include <NeuralNetwork.H>
Public Member Functions | |
NeuralLayer (int inputSize, int outputSize) | |
template<typename Derived > | |
NeuralLayer (const Eigen::MatrixBase< Derived > &weightsIn, const Eigen::MatrixBase< Derived > &biasIn) | |
virtual | ~NeuralLayer (void) |
Destructor. More... | |
virtual Eigen::Matrix< TYPE, Eigen::Dynamic, 1 > & | activate (const Eigen::Matrix< TYPE, Eigen::Dynamic, 1 > &input) |
Public Attributes | |
Eigen::Matrix< TYPE, Eigen::Dynamic, 1 > | output |
The output from this layer. More... | |
Protected Attributes | |
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... | |
Implements a single neural layer
TYPE | the precision of the data to use, e.g. float, double |
Definition at line 28 of file NeuralNetwork.H.
|
inline |
Generate a neural layer of particular size
inputSize | The number of the inputs |
outputSize | The number of outputs |
Definition at line 40 of file NeuralNetwork.H.
|
inline |
Generate a neural layer of particular size providing the weights
weightsIn | The weights to set |
biasIn | The biases to set |
Derived | is used by Eigen's Curiously recurring template pattern (CRTP) |
Definition at line 52 of file NeuralNetwork.H.
|
inlinevirtual |
Destructor.
Definition at line 59 of file NeuralNetwork.H.
|
inlinevirtual |
The activation function
This evaluates the neural network
input | The input to this layer |
Reimplemented in TanhLayer< TYPE >, and SigmoidLayer< TYPE >.
Definition at line 66 of file NeuralNetwork.H.
|
protected |
The biases for this layer.
Definition at line 31 of file NeuralNetwork.H.
Eigen::Matrix<TYPE, Eigen::Dynamic, 1> NeuralLayer< TYPE >::output |
The output from this layer.
Definition at line 34 of file NeuralNetwork.H.
|
protected |
The neural weights for this layer.
Definition at line 30 of file NeuralNetwork.H.