org.encog.neural.prune
public class PruneSelective extends Object
Constructor and Description |
---|
PruneSelective(BasicNetwork network)
Construct an object prune the neural network.
|
Modifier and Type | Method and Description |
---|---|
void |
changeNeuronCount(int layer,
int neuronCount)
Change the neuron count for the network.
|
double |
determineNeuronSignificance(int layer,
int neuron)
Determine the significance of the neuron.
|
BasicNetwork |
getNetwork() |
void |
prune(int targetLayer,
int neuron)
Prune one of the neurons from this layer.
|
void |
randomizeNeuron(double low,
double high,
int targetLayer,
int neuron) |
void |
randomizeNeuron(int targetLayer,
int neuron)
Assign random values to the network.
|
void |
stimulateNeuron(double percent,
int targetLayer,
int neuron)
Stimulate the specified neuron by the specified percent.
|
void |
stimulateWeakNeurons(int layer,
int count,
double percent)
Stimulate weaker neurons on a layer.
|
public PruneSelective(BasicNetwork network)
network
- The network to prune.public void changeNeuronCount(int layer, int neuronCount)
layer
- The layer to adjust.neuronCount
- The new neuron count for this layer.public double determineNeuronSignificance(int layer, int neuron)
layer
- The layer to query.neuron
- The neuron to query.public BasicNetwork getNetwork()
public void prune(int targetLayer, int neuron)
targetLayer
- The neuron to prune. Zero specifies the first neuron.neuron
- The neuron to prune.public void randomizeNeuron(double low, double high, int targetLayer, int neuron)
low
- The low-end of the range.high
- The high-end of the range.targetLayer
- The target layer.neuron
- The target neuron.public void randomizeNeuron(int targetLayer, int neuron)
targetLayer
- The target layer.neuron
- The target neuron.public void stimulateNeuron(double percent, int targetLayer, int neuron)
percent
- The percent to randomize by.targetLayer
- The layer that the neuron is on.neuron
- The neuron to randomize.public void stimulateWeakNeurons(int layer, int count, double percent)
layer
- The layer to stimulate.count
- The number of weak neurons to stimulate.percent
- The percent to stimulate by.Copyright © 2014. All Rights Reserved.