Evonet is the neural network taken from the EvoRobot. More...

Inheritance diagram for Evonet:

Signals
void	evonetUpdated ()
	emitted everytime the Evonet has been updated
Public Member Functions
void	computeParameters ()
void	configure (ConfigurationParameters &params, QString prefix)
	Configures the object using a ConfigurationParameters object.
void	copyPheParameters (int *pheGene)
void	create_net_block (int inputNeuronType, int hiddenNeuronType, int outputNeuronType, bool recurrentHiddens, bool inputOutputConnections, bool recurrentOutputs, bool biasOnHidden, bool biasOnOutput)
	create the block structure for a standard architecture create x-y coordinate for network architecture display store in local variable the number of neurons
int	freeParameters ()
float	getHidden (int h)
float	getInput (int in)
void	getMutations (float *mut)
float	getNeuron (int in)
int	getNoHiddens ()
int	getNoInputs ()
int	getNoNeurons ()
int	getNoOutputs ()
float *	getOldestStoredActivations ()
	Returns the oldest stored activation vector and removes it.
float	getOutput (int out)
int	getParamBias (int nbias)
void	getParameters (const int *dt)
float	getWrange ()
void	injectHidden (int nh, float val)
int	load_net_blocks (const char *filename, int mode)
	load the architecture and the free parameters of a controller mode=0, load only the architecture mode=1, load also the parameters
float	logistic (float f)
bool	pheFileLoaded ()
void	printBlocks ()
void	printIO ()
void	readNewPheLine (QStringList, float , float )
void	readOldPheLine (QStringList, float , float )
void	resetNet ()
void	save (ConfigurationParameters &params, QString prefix)
	Saves the actual status of parameters into the ConfigurationParameters object passed.
void	save_net_blocks (const char *filename, int mode)
int	setInput (int inp, float value)
void	setRanges (double weight, double bias, double gain)
void	updateNet ()
Static Public Member Functions
static void	describe (QString type)
	Add to Factory::typeDescriptions() the descriptions of all parameters and subgroups.
Public Attributes
QColor	neurondcolor [MAXN]
int	neurondisplay [MAXN]
char	neuronl [MAXN][10]
bool	neuronlesion [MAXN]
double	neuronlesionVal [MAXN]
double	neuronrange [MAXN][2]
Static Public Attributes
static const float	DEFAULT_VALUE = -99.0f
	DEFAULT_VALUE is used for do not assign values to mut and parameters.
static const int	MAXN = 1000
	Maximum number of neurons for a neural network of this type.
static const int	MAXSTOREDACTIVATIONS = 100
	The maximum number of stored activation vectors.
Friends
class	NetworkDialog
class	RendNetwork

Detailed Description

Evonet is the neural network taken from the EvoRobot.

Simple class to load a evorobot.net configuration file

Definition at line 48 of file evonet.h.

Member Function Documentation

void configure	(	ConfigurationParameters &	params,
		QString	prefix
	)		`[virtual]`

Configures the object using a ConfigurationParameters object.

Parameters:

params	the configuration parameters object with parameters to use
prefix	the prefix to use to access the object configuration parameters. This is guaranteed to end with the separator character when called by the factory, so you don't need to add one

Implements ParameterSettableWithConfigureFunction.

Definition at line 68 of file evonet.cpp.

References Evonet::create_net_block(), Evonet::DEFAULT_VALUE, Logger::error(), ConfigurationHelper::getBool(), ConfigurationHelper::getDouble(), ConfigurationHelper::getInt(), ConfigurationHelper::getString(), Evonet::load_net_blocks(), Evonet::MAXN, and ConfigurationHelper::throwUserConfigError().

void create_net_block	(	int	inputNeuronType,
		int	hiddenNeuronType,
		int	outputNeuronType,
		bool	recurrentHiddens,
		bool	inputOutputConnections,
		bool	recurrentOutputs,
		bool	biasOnHidden,
		bool	biasOnOutput
	)

create the block structure for a standard architecture create x-y coordinate for network architecture display store in local variable the number of neurons

Definition at line 205 of file evonet.cpp.

Referenced by Evonet::configure().

void describe ( QString type ) [static]

Add to Factory::typeDescriptions() the descriptions of all parameters and subgroups.

Reimplemented from ParameterSettable.

Definition at line 186 of file evonet.cpp.

void evonetUpdated ( ) [signal]

emitted everytime the Evonet has been updated

Note:: connect this signal to all necessary slots for updating the graphics stuff

float * getOldestStoredActivations ( )

Returns the oldest stored activation vector and removes it.

This returns the oldest activation vector and deletes it (memory is not freed, simply an internal index is incremented), so that subsequent calls will progressively return newer activation vectors. Returns NULL when no activation vector is stored