NeuralNetwork Class Reference
[Neural Network filtering]
#include <NeuralNetwork.h>
Public Types | |
| typedef std::vector < boost::shared_ptr < GeneralNeuron > > | tNeuralLayer |
| typedef std::vector< tNeuralLayer > | tNeuralArray |
| typedef std::vector < SigmoidalNeuron::tneurontype > | ttypeVector |
| typedef std::vector< ttypeVector > | ttypeArray |
Public Member Functions | |
| void | SetAlpha (const double a) |
| Set the momentum multiplier. | |
| void | SetMu (const double m) |
| Set the adaptation stepsize. | |
| void | SetLayers (ttypeArray typeArray, bool cachedoutput=false) |
| Configure the layers of the network according to the types in typeArray. | |
| void | InitWeights (const double MaxWeight, const double MaxBias) |
| Initialize the weights with random values with the specified maxima. | |
| void | PrintTopology (std::string filename) |
| Print the topology and weights of the network for plotting with the dot program. | |
| virtual void | PrintWeights (std::ostream &output) |
| Print the weights of the network to the specified output stream. | |
| virtual const gplib::rvec & | GetWeightsAsVector () |
| Return the network weights as a single vector. | |
| virtual void | AdaptFilter (const gplib::rvec &Input, const gplib::rvec &Desired) |
| Adapt the Filter with the current input and desired. | |
| virtual void | CalcOutput (const gplib::rvec &Input, gplib::rvec &Output) |
| Calculate the output with the given input. | |
| NeuralNetwork (const int inputsize, const int outputsize) | |
| The minium values for the network are the length of the input and output. | |
| NeuralNetwork (const int inputsize, const int outputsize, const double mu_, const ttypeArray &Layerssetup, const double maxinit, bool cachedoutput=false) | |
| Extended constructor with most of the necessary values. | |
| virtual | ~NeuralNetwork () |
Detailed Description
The class NeuralNetwork manages the network output calculation, neuron storage and weight adaptation Derived from AdaptiveFilter so we can use the Filter functionalityDefinition at line 16 of file NeuralNetwork.h.
Member Typedef Documentation
| typedef std::vector<tNeuralLayer> NeuralNetwork::tNeuralArray |
Definition at line 19 of file NeuralNetwork.h.
| typedef std::vector<boost::shared_ptr<GeneralNeuron> > NeuralNetwork::tNeuralLayer |
Definition at line 18 of file NeuralNetwork.h.
| typedef std::vector<ttypeVector > NeuralNetwork::ttypeArray |
Definition at line 21 of file NeuralNetwork.h.
| typedef std::vector<SigmoidalNeuron::tneurontype> NeuralNetwork::ttypeVector |
Definition at line 20 of file NeuralNetwork.h.
Constructor & Destructor Documentation
The minium values for the network are the length of the input and output.
Definition at line 9 of file NeuralNetwork.cpp.
| NeuralNetwork::NeuralNetwork | ( | const int | inputsize, | |
| const int | outputsize, | |||
| const double | mu_, | |||
| const ttypeArray & | Layerssetup, | |||
| const double | maxinit, | |||
| bool | cachedoutput = false | |||
| ) |
Extended constructor with most of the necessary values.
Definition at line 18 of file NeuralNetwork.cpp.
References InitWeights(), and SetLayers().
| NeuralNetwork::~NeuralNetwork | ( | ) | [virtual] |
Definition at line 31 of file NeuralNetwork.cpp.
Member Function Documentation
| void NeuralNetwork::AdaptFilter | ( | const gplib::rvec & | Input, | |
| const gplib::rvec & | Desired | |||
| ) | [virtual] |
Adapt the Filter with the current input and desired.
Implements AdaptiveFilter.
Definition at line 34 of file NeuralNetwork.cpp.
References AdaptiveFilter::GetFilterOutput(), and AdaptiveFilter::SetEpsilon().
Referenced by main().
| void NeuralNetwork::CalcOutput | ( | const gplib::rvec & | Input, | |
| gplib::rvec & | Output | |||
| ) | [virtual] |
Calculate the output with the given input.
Implements AdaptiveFilter.
Definition at line 43 of file NeuralNetwork.cpp.
References AdaptiveFilter::SetOutput().
| const gplib::rvec & NeuralNetwork::GetWeightsAsVector | ( | ) | [virtual] |
Return the network weights as a single vector.
Implements AdaptiveFilter.
Definition at line 55 of file NeuralNetwork.cpp.
References size.
Referenced by PrintTopology().
Initialize the weights with random values with the specified maxima.
Definition at line 117 of file NeuralNetwork.cpp.
References UniformRNG::GetNumber().
Referenced by main(), and NeuralNetwork().
| void NeuralNetwork::PrintTopology | ( | std::string | filename | ) |
Print the topology and weights of the network for plotting with the dot program.
Definition at line 212 of file NeuralNetwork.cpp.
References GetWeightsAsVector(), and size.
Referenced by main().
| void NeuralNetwork::PrintWeights | ( | std::ostream & | output | ) | [virtual] |
Print the weights of the network to the specified output stream.
Implements AdaptiveFilter.
Definition at line 200 of file NeuralNetwork.cpp.
Referenced by main().
| void NeuralNetwork::SetAlpha | ( | const double | a | ) | [inline] |
| void NeuralNetwork::SetLayers | ( | ttypeArray | typeArray, | |
| bool | cachedoutput = false | |||
| ) |
Configure the layers of the network according to the types in typeArray.
Definition at line 78 of file NeuralNetwork.cpp.
Referenced by main(), and NeuralNetwork().
| void NeuralNetwork::SetMu | ( | const double | m | ) | [inline] |
The documentation for this class was generated from the following files:
