TarzaNN
TarzaNN neural network simulator
Public Member Functions | Protected Member Functions | Friends
STSOMFeaturePlane Class Reference

A Topographic Self Organizing map fp, with continuous transformation learning. More...

#include <STSOMFeaturePlane.h>

Inheritance diagram for STSOMFeaturePlane:
LearningFeaturePlane FeaturePlane FeaturePlaneAbstract Observer Viewable

List of all members.

Public Member Functions

 ~STSOMFeaturePlane ()
void read (QDataStream *inStream, QProgressDialog *progress, int *index)
void save (QDataStream *outStream, QProgressDialog *progress, int *index)
bool isLearning ()
FeaturePlaneInputaddFilter (Filter *f, FeaturePlaneAbstract *fp, int type, int fpOutputIndex, bool wta)
void incWinCount ()
int getWinCount ()

Protected Member Functions

 STSOMFeaturePlane (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)
void step ()
float nonlinearity (Matrix *totalActivation, OutputImage *workOutput)
void computeGatingUnits ()
MatrixgetTotalActivation ()
bool hasConverged ()

Friends

class GatingUnits
class FeaturePlaneFactory

Detailed Description

A Topographic Self Organizing map fp, with continuous transformation learning.


Constructor & Destructor Documentation

STSOMFeaturePlane::~STSOMFeaturePlane ( )
STSOMFeaturePlane::STSOMFeaturePlane ( 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]

Constructor

Parameters:
net- network, this FP will be added to the end of the list of feature planes
l- layer index
name- name of the feature plane
w- width
h- height
angles- number of discrete angles (e.g. speeds, orientations)
speeds- number of speeds (e.g. speed bands, scale bands)
alpha- alpha
speed- speed of this fp
isWTA- participates in Selective Tuning
visible- should the FP be presented in the UI
neuron- neuron strategy (what is the output nonlinearity, or the ODE that defines response)
notify- notification strategy (deprecated, on the way out)
learning- are weights adjustable through learning?

Member Function Documentation

FeaturePlaneInput * STSOMFeaturePlane::addFilter ( Filter f,
FeaturePlaneAbstract fp,
int  type,
int  fpOutputIndex,
bool  wta 
) [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 LearningFeaturePlane.

void STSOMFeaturePlane::computeGatingUnits ( ) [protected]

Reimplemented from LearningFeaturePlane.

Matrix * STSOMFeaturePlane::getTotalActivation ( ) [protected]
int STSOMFeaturePlane::getWinCount ( ) [inline]
bool STSOMFeaturePlane::hasConverged ( ) [inline, protected]
void STSOMFeaturePlane::incWinCount ( ) [inline]
bool STSOMFeaturePlane::isLearning ( )
float STSOMFeaturePlane::nonlinearity ( Matrix totalActivation,
OutputImage workOutput 
) [protected]
void STSOMFeaturePlane::read ( QDataStream *  inStream,
QProgressDialog *  progress,
int *  index 
) [virtual]

Implements LearningFeaturePlane.

void STSOMFeaturePlane::save ( QDataStream *  outStream,
QProgressDialog *  progress,
int *  index 
) [virtual]

Implements LearningFeaturePlane.

void STSOMFeaturePlane::step ( ) [protected, virtual]

Do one computation step - compute activations, and FP output

Reimplemented from FeaturePlane.


Friends And Related Function Documentation

friend class FeaturePlaneFactory [friend]

Reimplemented from LearningFeaturePlane.

friend class GatingUnits [friend]

Reimplemented from LearningFeaturePlane.


The documentation for this class was generated from the following files:
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Defines