Method | Description | |
---|---|---|
TrainFlatNetworkResilient ( |
Tran a network using RPROP.
|
|
TrainFlatNetworkResilient ( |
Construct a resilient trainer for flat networks.
|
|
UpdateWeight ( double gradients, double lastGradient, int index ) : double |
Calculate the amount to change the weight by.
|
Method | Description | |
---|---|---|
Sign ( double value ) : int |
Determine the sign of the value.
|
public TrainFlatNetworkResilient ( |
||
flat | The network to train. | |
trainingSet | IEngineDataSet | The training data to use. |
return | Encog.Engine.Data |
public TrainFlatNetworkResilient ( |
||
network | 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. |
return | Encog.Engine.Data |
public UpdateWeight ( double gradients, double lastGradient, int index ) : double | ||
gradients | double | The gradients. |
lastGradient | double | The last gradients. |
index | int | The index to update. |
return | double |