#include <FeedForwardNeuralNetwork.h>
Inheritance diagram for Teem::BackPropFeedForwardNeuralNetwork:
Use that way:
for i in inputs nn.setInput(i, inputValue); nn.step();Ishtar::Variable<bool> outputLayerRecursive; for i in outputs nn.setError(i, errorValue); nn.stepBackward();
Public Member Functions | |
BackPropFeedForwardNeuralNetwork (size_t inputCount, size_t outputCount, const std::string &root) | |
Constructor, create a feed forward neural network with online back-propagation with inputCount inputs and outputCount outputs. | |
virtual | ~BackPropFeedForwardNeuralNetwork () |
Destructor. | |
virtual void | stepBackward () |
Backpropagate the error on the weight. | |
void | setError (size_t index, double val) |
Set the desired output (used for back-propagation of error). | |
void | setLearningRate (double rate) |
Set the learning rate value. | |
double | getLearningRate () |
Get the learning rate value. | |
Static Protected Member Functions | |
static double | TanhBackwardActivationFunction (double x, double b) |
Tanh backward activation function. | |
Protected Attributes | |
Ishtar::Variable< double > | learningRate |
learning rate constant | |
std::valarray< double > | error |
desired output | |
ActivationFunction | backwardActFunc |
derivative of the activation function | |
std::vector< std::valarray< double > > | deltas |
deltas (see backprop algorithm) |