Inheritance diagram for LearningFeaturePlane:

Public Member Functions
	~LearningFeaturePlane ()
virtual void	read (QDataStream inStream, QProgressDialog progress, int *index)=0
virtual void	save (QDataStream outStream, QProgressDialog progress, int *index)=0
Protected Member Functions
	LearningFeaturePlane (Network net, int l, QString name, int w, int h, int angles, int speeds, int alpha, int speed, bool isWTA, bool visible, Neuron neuron, NotifyStrategyAbstract notify, bool learning)
FeaturePlaneInput *	addFilter (Filter f, FeaturePlaneAbstract fp, int type, int fpOutputIndex, bool wta)
float	computeSkip (int input, int output, int filter)
void	setWindowRange (int input_width, int input_height, int filter_width, int filter_height)
void	computeGatingUnits ()
Protected Attributes
PlaneInputWindowSet *	windows
Matrix *	activations
Matrix *	desiredOutcome
Matrix *	errorMatrix
vector< Matrix * >	backErrorMatrix
bool	learning
vector< FilterBank * >	inputFilters
float	ita
Friends
class	GatingUnits
class	FeaturePlaneFactory

Detailed Description

It loads an image file (PNG, BMP, XBM, XPM, PNM, and possibly JPG, GIF, MNG, based on how QT was compiled - see QImageIO) and offers it as output.

Constructor & Destructor Documentation

LearningFeaturePlane::~LearningFeaturePlane ( )

LearningFeaturePlane::LearningFeaturePlane	(	Network *	net,
		int	l,
		QString *	name,
		int	w,
		int	h,
		int	angles,
		int	speeds,
		int	alpha,
		int	speed,
		bool	isWTA,
		bool	visible,
		Neuron *	neuron,
		NotifyStrategyAbstract *	notify,
		bool	learning
	)		`[protected]`

Load the specified file

Parameters:

net	- network, this FP will be added to the end of the list of feature planes
filename	- file to open as input
name	- name of the feature plane
visible	- should the FP be presented in the UI
scale	- to scale or not to scale, this is the question
min	- scale currentOutput to the min - max range
max

FeaturePlaneInput * LearningFeaturePlane::addFilter	(	Filter *	f,
		FeaturePlaneAbstract *	fp,
		int	type,
		int	fpOutputIndex,
		bool	wta
	)		`[protected, virtual]`

Add an input filter/feature plane pair.

Parameters:

f	- filter
fp	- input feature plane
type	- input type: regular, non-Fourier, masking
fpOutputIndex	- in case input feature plane has more than one output, which one are we interested in

Reimplemented from FeaturePlane.

void LearningFeaturePlane::computeGatingUnits ( ) [protected]