Class ILNeuralNetwork.TILNeuralNetworkRPropTrain

From Mitov Wiki Doc
(Difference between revisions)
Jump to: navigation, search
(Automated Syncronization with Documentation)
(Automated Syncronization with Documentation)
Line 34: Line 34:
  
 
== Description ==
 
== Description ==
This component is designed to train neural networks using RProp
+
This component is designed to train neural networks using
algorithm.
+
RProp algorithm.
  
 
To use the component set the Neural Network to be trained in
 
To use the component set the Neural Network to be trained in
 
the NeuralNetwork property.
 
the NeuralNetwork property.
 +
 +
 +
 +
<b>Diagram:</b>
 +
 +
[[Image:ILNeuralNetworkRPropTrain_Preview.png]]
  
 
== Properties ==
 
== Properties ==
Line 53: Line 59:
 
*[[Property ILNeuralNetwork.TILNeuralNetworkTrain.TerminationCriteria|TerminationCriteria]] - Criteria for terminating the training.  
 
*[[Property ILNeuralNetwork.TILNeuralNetworkTrain.TerminationCriteria|TerminationCriteria]] - Criteria for terminating the training.  
 
*[[Property ILNeuralNetwork.TILNeuralNetworkTrain.NormalizeTrainingWeights|NormalizeTrainingWeights]] - Specifies if the weights should be normalized.  
 
*[[Property ILNeuralNetwork.TILNeuralNetworkTrain.NormalizeTrainingWeights|NormalizeTrainingWeights]] - Specifies if the weights should be normalized.  
 +
*[[Property ILNeuralNetwork.TILNeuralNetworkTrain.ScaleInputs|ScaleInputs]] - Scales the inputs before the training.
 +
*[[Property ILNeuralNetwork.TILNeuralNetworkTrain.ScaleOutputs|ScaleOutputs]] - Scales the outputs before the training.
  
 
== Methods ==
 
== Methods ==
Line 58: Line 66:
 
=== Public ===
 
=== Public ===
 
*[[Method function ILNeuralNetwork.TILNeuralNetworkTrain.Train(IILTrainingDataArray) : Integer|function Train(AData : IILTrainingDataArray) : Integer]] - Trains the connected neural network.  
 
*[[Method function ILNeuralNetwork.TILNeuralNetworkTrain.Train(IILTrainingDataArray) : Integer|function Train(AData : IILTrainingDataArray) : Integer]] - Trains the connected neural network.  
*[[Method function ILNeuralNetwork.TILNeuralNetworkTrain.Train(array;array) : Integer|function Train(ATraingFeatures : array; AResposes : array) : Integer]]
+
*[[Method function ILNeuralNetwork.TILNeuralNetworkTrain.Train(ISLRealBuffer;ISLRealBuffer) : Integer|function Train(ATraingFeatures : ISLRealBuffer; AResposes : ISLRealBuffer) : Integer]]
*[[Method function ILNeuralNetwork.TILNeuralNetworkTrain.Train(array;array;array) : Integer|function Train(ATraingFeatures : array; AResposes : array; AWeights : array) : Integer]]
+
*[[Method function ILNeuralNetwork.TILNeuralNetworkTrain.Train(ISLRealBuffer;ISLRealBuffer;Real) : Integer|function Train(ATraingFeatures : ISLRealBuffer; AResposes : ISLRealBuffer; AWeights : Real) : Integer]]
 
*[[Method function ILNeuralNetwork.TILNeuralNetworkTrain.Train(ISLRealBufferArray;ISLRealBufferArray) : Integer|function Train(ATraingFeatures : ISLRealBufferArray; AResposes : ISLRealBufferArray) : Integer]] - Trains the connected neural network.  
 
*[[Method function ILNeuralNetwork.TILNeuralNetworkTrain.Train(ISLRealBufferArray;ISLRealBufferArray) : Integer|function Train(ATraingFeatures : ISLRealBufferArray; AResposes : ISLRealBufferArray) : Integer]] - Trains the connected neural network.  
 
*[[Method function ILNeuralNetwork.TILNeuralNetworkTrain.Train(ISLRealBufferArray;ISLRealBufferArray;ISLRealBuffer) : Integer|function Train(ATraingFeatures : ISLRealBufferArray; AResposes : ISLRealBufferArray; AWeights : ISLRealBuffer) : Integer]] - Trains the connected neural network.  
 
*[[Method function ILNeuralNetwork.TILNeuralNetworkTrain.Train(ISLRealBufferArray;ISLRealBufferArray;ISLRealBuffer) : Integer|function Train(ATraingFeatures : ISLRealBufferArray; AResposes : ISLRealBufferArray; AWeights : ISLRealBuffer) : Integer]] - Trains the connected neural network.  
Line 69: Line 77:
 
== Events ==
 
== Events ==
 
*[[Event ILNeuralNetwork.TILNeuralNetworkTrain.OnProgress|OnProgress]] - Training progress notification event.  
 
*[[Event ILNeuralNetwork.TILNeuralNetworkTrain.OnProgress|OnProgress]] - Training progress notification event.  
 +
*[[Event ILNeuralNetwork.TILNeuralNetworkTrain.OnError|OnError]] - Occurs on training error.
  
 
[[Category:Components]][[Category:Classes]]
 
[[Category:Components]][[Category:Classes]]

Revision as of 20:30, 10 June 2013

This is a Beta Read Only version of this page. Please review and send recommendations to mitov@mitov.com. We will enable the editing as soon as we are happy with the overall Wiki site.

BIGILNeuralNetworkRPropTrain.gif ILNeuralNetworkRPropTrain.gif NETILNeuralNetworkRPropTrain.gif

Package: IntelligenceLabPkg

Unit: ILNeuralNetwork

Inherits: TILNeuralNetworkTrain

Contents

Syntax

Delphi:

type TILNeuralNetworkRPropTrain = class( TILNeuralNetworkTrain )

C++ Builder:

class TILNeuralNetworkRPropTrain : public TILNeuralNetworkTrain

Visual C++ (MFC):

class CTILNeuralNetworkRPropTrain : public CTILNeuralNetworkTrain

C# (.NET):

public ref class TILNeuralNetworkRPropTrain : Mitov.IntelligenceLab.NeuralNetworkTrain

Summary

Trains neural networks using RProp algorithm.

Description

This component is designed to train neural networks using RProp algorithm.

To use the component set the Neural Network to be trained in the NeuralNetwork property.


Diagram:

ILNeuralNetworkRPropTrain Preview.png

Properties

Published

From TILNeuralNetworkTrain

Properties

Published

Methods

Public

Pins

Events

Personal tools
Namespaces
Variants
Actions
Navigation
Toolbox