Teem::BackPropFeedForwardNeuralNetwork Class Reference
[Controllers and neural networks]

#include <FeedForwardNeuralNetwork.h>

Inheritance diagram for Teem::BackPropFeedForwardNeuralNetwork:

List of all members.

---

Detailed Description

Feed forward neural network with online back-propagation.

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)

---

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

• controller/nn/FeedForwardNeuralNetwork.h
• controller/nn/FeedForwardNeuralNetwork.cpp

---