C# 클래스 xpidea.neuro.net.son.SelfOrganizingNetwork

Implements the Self Organizing Network (SON).

The basic Self-Organizing Network can be visualized as a sheet-like neural-network array , the cells (or nodes) of which become specifically tuned to various input signal patterns or classes of patterns in an orderly fashion. The learning process is competitive and unsupervised, meaning that no teacher is needed to define the correct output (or actually the cell into which the input is mapped) for an input. In the basic version, only one map node (winner) at a time is activated corresponding to each input. The locations of the responses in the array tend to become ordered in the learning process as if some meaningful nonlinear coordinate system for the different input features were being created over the network (Kohonen, 1995c).The SOM was developed by Prof. Teuvo Kohonen in the early 1980s. The first application area of the SOM was speech recognition, or perhaps more accurately, speech-to-text transformation. (Timo Honkela)

상속: xpidea.neuro.net.adaline.AdalineNetwork

파일 보기 프로젝트 열기: AlexCherkasov/Neuro.NET

보호된 프로퍼티들

프로퍼티	타입	설명
columsCount	int
currentIteration	long
currentNeighborhoodSize	int
finalLearningRate	double
initialLearningRate	double
initialNeighborhoodSize	int
kohonenLayer	].NeuroNode[
neighborhoodReduceInterval	int
rowsCount	int
trainingIterations	long
winnigCol	int
winnigRow	int

공개 메소드들

메소드	설명
Epoch ( int epoch ) : void	Overridden.Epoch - number of patterns that was exposed to a network during one training cycle.
Learn ( ) : void	Overridden.Teaches the network.
Load ( BinaryReader binaryReader ) : void	Overridden.Loads network data from the binary stream.
Run ( ) : void	Overridden.Runs the network.
Save ( BinaryWriter binaryWriter ) : void	Overridden.Stores network into to a binary stream.
SelfOrganizingNetwork ( ) : System	Constructs uninitialized instance of SON network. Used for persistance purposes.
SelfOrganizingNetwork ( int aInputNodesCount, int aRowCount, int aColCount, double aInitialLearningRate, double aFinalLearningRate, int aInitialNeighborhoodSize, int aNeighborhoodReduceInterval, long aTrainingIterationsCount ) : System	Constructs the network.
SelfOrganizingNetwork ( string fileName ) : System	Creates the network from a file.
Train ( PatternsCollection patterns ) : void	Overridden.Trains the network.

보호된 메소드들

메소드	설명
CreateNetwork ( ) : void	Overridden.Constructs network topology.
GetInputNode ( int index ) : NeuroNode	Overridden.Retrieves the input node by its index.
GetInputNodesCount ( ) : int	Overridden.Returns number of nodes in input layer.
GetNetworkType ( ) : NeuralNetworkType	Overridden.Returns xpidea.neuro.net.NeuralNetworkType.nntSON for SON network.
GetNodeError ( ) : double	Overridden.Always returns 0. There is no output node.
GetOutPutNodesCount ( ) : int	Overridden.Number of nodes in output layer. Always return 0 since there are no nodes as its have an Kohonen layer.
GetOutputNode ( int index ) : NeuroNode	Overridden.Returns an output node by its index.
SetNodeError ( double value ) : void	Overridden.Doesn't do anything. There is no output node.

메소드 상세

CreateNetwork() 보호된 메소드

Overridden.Constructs network topology.

protected CreateNetwork ( ) : void
리턴	void

Epoch() 공개 메소드

Overridden.Epoch - number of patterns that was exposed to a network during one training cycle.

public Epoch ( int epoch ) : void
epoch	int
리턴	void

GetInputNode() 보호된 메소드

Overridden.Retrieves the input node by its index.

protected GetInputNode ( int index ) : NeuroNode
index	int	Input node index.
리턴	NeuroNode

GetInputNodesCount() 보호된 메소드

Overridden.Returns number of nodes in input layer.

protected GetInputNodesCount ( ) : int
리턴	int

GetNetworkType() 보호된 메소드

Overridden.Returns xpidea.neuro.net.NeuralNetworkType.nntSON for SON network.

protected GetNetworkType ( ) : NeuralNetworkType
리턴	NeuralNetworkType

GetNodeError() 보호된 메소드

Overridden.Always returns 0. There is no output node.

protected GetNodeError ( ) : double
리턴	double

GetOutPutNodesCount() 보호된 메소드

Overridden.Number of nodes in output layer. Always return 0 since there are no nodes as its have an Kohonen layer.

protected GetOutPutNodesCount ( ) : int
리턴	int

GetOutputNode() 보호된 메소드

Overridden.Returns an output node by its index.

protected GetOutputNode ( int index ) : NeuroNode
index	int	Output node index.
리턴	NeuroNode

Learn() 공개 메소드

Overridden.Teaches the network.

public Learn ( ) : void
리턴	void

Load() 공개 메소드

Overridden.Loads network data from the binary stream.

public Load ( BinaryReader binaryReader ) : void
binaryReader	System.IO.BinaryReader	Binary stream reader.
리턴	void

Run() 공개 메소드

Overridden.Runs the network.

public Run ( ) : void
리턴	void

Save() 공개 메소드

Overridden.Stores network into to a binary stream.

public Save ( BinaryWriter binaryWriter ) : void
binaryWriter	System.IO.BinaryWriter	Binary stream writer.
리턴	void

SelfOrganizingNetwork() 공개 메소드

Constructs uninitialized instance of SON network. Used for persistance purposes.

public SelfOrganizingNetwork ( ) : System
리턴	System

SelfOrganizingNetwork() 공개 메소드

Constructs the network.

public SelfOrganizingNetwork ( int aInputNodesCount, int aRowCount, int aColCount, double aInitialLearningRate, double aFinalLearningRate, int aInitialNeighborhoodSize, int aNeighborhoodReduceInterval, long aTrainingIterationsCount ) : System
aInputNodesCount	int	Number of input nodes.
aRowCount	int	Number of rows in output layer.
aColCount	int	Number of colums in output layer.
aInitialLearningRate	double	Starting learning rate.
aFinalLearningRate	double	Ending learning rate.
aInitialNeighborhoodSize	int	Initial neighborhood size.
aNeighborhoodReduceInterval	int	Number of training iterations after neighborhood size will be reduced.
aTrainingIterationsCount	long	Number of training iterations.
리턴	System

SelfOrganizingNetwork() 공개 메소드

Creates the network from a file.

public SelfOrganizingNetwork ( string fileName ) : System
fileName	string
리턴	System

SetNodeError() 보호된 메소드

Overridden.Doesn't do anything. There is no output node.

protected SetNodeError ( double value ) : void
value	double	Error value.
리턴	void

Train() 공개 메소드

Overridden.Trains the network.

public Train ( PatternsCollection patterns ) : void
patterns	xpidea.neuro.net.patterns.PatternsCollection
리턴	void

프로퍼티 상세

columsCount 보호되어 있는 프로퍼티

Number of colums in output layer.

protected int columsCount
리턴	int

currentIteration 보호되어 있는 프로퍼티

Current iteration.

protected long currentIteration
리턴	long

currentNeighborhoodSize 보호되어 있는 프로퍼티

Current neighborhood size.

protected int currentNeighborhoodSize
리턴	int

finalLearningRate 보호되어 있는 프로퍼티

Final learning rate.

protected double finalLearningRate
리턴	double

initialLearningRate 보호되어 있는 프로퍼티

Initial learning rate.

protected double initialLearningRate
리턴	double

initialNeighborhoodSize 보호되어 있는 프로퍼티

Initial neighborhood size.

protected int initialNeighborhoodSize
리턴	int

kohonenLayer 보호되어 있는 프로퍼티

Represents the Kohonen layer as two-dimetional array of xpidea.neuro.net.NeuroNode.

protected NeuroNode[,] kohonenLayer
리턴	].NeuroNode[

neighborhoodReduceInterval 보호되어 있는 프로퍼티

Neighborhood reduce interval.

protected int neighborhoodReduceInterval
리턴	int

rowsCount 보호되어 있는 프로퍼티

Number of rows in output layer.

protected int rowsCount
리턴	int

trainingIterations 보호되어 있는 프로퍼티

Number of training iterations.

protected long trainingIterations
리턴	long

winnigCol 보호되어 있는 프로퍼티

Winning column in output layer.

protected int winnigCol
리턴	int

winnigRow 보호되어 있는 프로퍼티

Winning row in output layer.

protected int winnigRow
리턴	int