Class ILNeuralNetwork.TILNeuralNetworkBackpropTrain

Revision as of 00:12, 26 June 2013 (view source) David Alm (Talk | contribs) (Automated Syncronization with Documentation) ← Older edit		Latest revision as of 00:32, 26 June 2013 (view source) David Alm (Talk | contribs) (Automated Syncronization with Documentation)
Line 28:		Line 28:
	=== C# (.NET): ===		=== C# (.NET): ===
	<code>		<code>
−	'''public ref class''' TILNeuralNetworkBackpropTrain : [[Class ILNeuralNetwork.TILNeuralNetworkTrain|Mitov.IntelligenceLab.NeuralNetworkTrain]]	+	'''public ref class''' NeuralNetworkBackpropTrain : [[Class ILNeuralNetwork.TILNeuralNetworkTrain|Mitov.IntelligenceLab.NeuralNetworkTrain]]
	</code>		</code>
	== Summary ==		== Summary ==

---

Latest revision as of 00:32, 26 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.

Package: IntelligenceLabPkg

Unit: ILNeuralNetwork

Inherits: TILNeuralNetworkTrain

Contents 1 Syntax 1.1 Delphi: 1.2 C++ Builder: 1.3 Visual C++ (MFC): 1.4 C# (.NET): 2 Summary 3 Description 4 Properties 4.1 Published 5 From TILNeuralNetworkTrain 6 Properties 6.1 Published 7 Methods 7.1 Public 8 Pins 9 Events

Syntax

Delphi:

type TILNeuralNetworkBackpropTrain = class( TILNeuralNetworkTrain )

C++ Builder:

class TILNeuralNetworkBackpropTrain : public TILNeuralNetworkTrain

Visual C++ (MFC):

class CTILNeuralNetworkBackpropTrain : public CTILNeuralNetworkTrain

C# (.NET):

public ref class NeuralNetworkBackpropTrain : Mitov.IntelligenceLab.NeuralNetworkTrain

Summary

Trains neural networks using Backprop algorithm.

Description

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

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

Diagram:

Properties

Published

• Weights - Specifies the training weights.

From TILNeuralNetworkTrain

Properties

Published

• NeuralNetwork - Specifies the Neural Network component to be trained.
• TerminationCriteria - Criteria for terminating the training.
• NormalizeTrainingWeights - Specifies if the weights should be normalized.
• ScaleInputs - Scales the inputs before the training.
• ScaleOutputs - Scales the outputs before the training.

Methods

Public

• function Train(AData : IILTrainingDataArray) : Integer - Trains the connected neural network.
• function Train(ATraingFeatures : ISLRealBuffer; AResposes : ISLRealBuffer) : Integer
• function Train(ATraingFeatures : ISLRealBuffer; AResposes : ISLRealBuffer; AWeights : Real) : Integer
• function Train(ATraingFeatures : ISLRealBufferArray; AResposes : ISLRealBufferArray) : Integer - Trains the connected neural network.
• function Train(ATraingFeatures : ISLRealBufferArray; AResposes : ISLRealBufferArray; AWeights : ISLRealBuffer) : Integer - Trains the connected neural network.

Pins

• InputPin - The training data input pin of the component.
• ProgressPin - The Training Progress Pin.

Events

• OnProgress - Training progress notification event.
• OnError - Occurs on training error.