C# Класс Encog.Engine.Network.Train.Prop.TrainFlatNetworkResilient

Train a flat network using RPROP.
Наследование: TrainFlatNetworkProp
Показать файл Открыть проект Примеры использования класса

Открытые методы

Метод Описание
TrainFlatNetworkResilient ( FlatNetwork flat, IEngineDataSet trainingSet ) : Encog.Engine.Data

Tran a network using RPROP.
TrainFlatNetworkResilient ( FlatNetwork network, IEngineDataSet training, double zeroTolerance, double initialUpdate, double maxStep ) : Encog.Engine.Data

Construct a resilient trainer for flat networks.
UpdateWeight ( double gradients, double lastGradient, int index ) : double

Calculate the amount to change the weight by.

Приватные методы

Метод Описание
Sign ( double value ) : int

Determine the sign of the value.

Описание методов

TrainFlatNetworkResilient() публичный Метод

Tran a network using RPROP.
public TrainFlatNetworkResilient ( FlatNetwork flat, IEngineDataSet trainingSet ) : Encog.Engine.Data
flat Encog.Engine.Network.Flat.FlatNetwork The network to train.
trainingSet IEngineDataSet The training data to use.
Результат Encog.Engine.Data

TrainFlatNetworkResilient() публичный Метод

Construct a resilient trainer for flat networks.
public TrainFlatNetworkResilient ( FlatNetwork network, IEngineDataSet training, double zeroTolerance, double initialUpdate, double maxStep ) : Encog.Engine.Data
network Encog.Engine.Network.Flat.FlatNetwork The network to train.
training IEngineDataSet The training data to use.
zeroTolerance double How close a number should be to zero to be counted as zero.
initialUpdate double The initial update value.
maxStep double The maximum step value.
Результат Encog.Engine.Data

UpdateWeight() публичный Метод

Calculate the amount to change the weight by.
public UpdateWeight ( double gradients, double lastGradient, int index ) : double
gradients double The gradients.
lastGradient double The last gradients.
index int The index to update.
Результат double