public class Gradient extends Object
| Constructor and Description |
|---|
Gradient(org.encog.neural.flat.FlatNetwork theNetwork,
org.encog.ml.data.MLDataSet theTraining,
double[] flatSpot,
org.encog.neural.error.ErrorFunction ef)
Construct a gradient worker.
|
| Modifier and Type | Method and Description |
|---|---|
double |
getError() |
org.encog.mathutil.error.ErrorCalculation |
getErrorCalculation() |
double[] |
getGradients() |
double[] |
getLayerDelta() |
org.encog.neural.flat.FlatNetwork |
getNetwork() |
double[] |
getWeights() |
void |
run()
Perform the gradient calculation
|
void |
setParams(org.encog.neural.networks.BasicNetwork network) |
void |
setWeights(double[] weights) |
public Gradient(org.encog.neural.flat.FlatNetwork theNetwork,
org.encog.ml.data.MLDataSet theTraining,
double[] flatSpot,
org.encog.neural.error.ErrorFunction ef)
theNetwork - The network to train.theOwner - The owner that is doing the training.theTraining - The training data.theLow - The low index to use in the training data.theHigh - The high index to use in the training data.public final void run()
public org.encog.mathutil.error.ErrorCalculation getErrorCalculation()
public double[] getGradients()
public double getError()
public double[] getWeights()
public void setWeights(double[] weights)
weights - the weights to setpublic void setParams(org.encog.neural.networks.BasicNetwork network)
public org.encog.neural.flat.FlatNetwork getNetwork()
public double[] getLayerDelta()
Copyright © 2015. All Rights Reserved.