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

#include <FeedForwardNeuralNetwork.h>

Inheritance diagram for Teem::RecurrentFeedForwardNeuralNetwork:

List of all members.

---

Detailed Description

Feed forward neural network with optional recurence for each layer.

Public Member Functions
	RecurrentFeedForwardNeuralNetwork (size_t inputCount, size_t outputCount, const std::string &root)
	Constructor, create a recurrent neural network with inputCount inputs and outputCount outputs.
virtual	~RecurrentFeedForwardNeuralNetwork ()
	Destructor.
virtual void	step ()
	Propagate the input values to the output through all the layers.
virtual void	randomize (double from, double to)
	Put random weights with uniform distribution.
void	setRecursiveWeight (size_t layer, size_t from, size_t to, double w)
	Set the recursive weight in a layer.
double	getRecursiveWeight (size_t layer, size_t from, size_t to) const
	Get the value for a particular recursive weight.
bool	isLayerRecursive (size_t layer)
	Return true if layer is recurrent.
Protected Attributes
Ishtar::Variable< bool >	outputLayerRecursive
	is output layer recursive?
std::vector< Matrix< double > >	recursiveWeights
	recusive weights for each layer
std::vector< bool >	layerRecursive
	is layer recursive?

---

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

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

---