public class HNeuralNet extends Object
Constructor and Description |
---|
HNeuralNet()
Create a network net and set name for the network
|
Modifier and Type | Method and Description |
---|---|
void |
addFeedForwardLayer(int neuronCount)
Construct this layer with a sigmoid threshold function.
|
void |
doc()
Show online documentation.
|
org.encog.neural.data.basic.BasicNeuralDataSet |
editData()
Edit data
|
org.encog.neural.networks.BasicNetwork |
editNetwork()
Edit a neural net in a frame
|
org.encog.neural.data.basic.BasicNeuralDataSet |
getData()
Get data
|
ArrayList<Double> |
getEpochError()
Returns errors for each epoch.
|
org.encog.neural.networks.Network |
getNetwork()
Return neural net back.
|
org.encog.neural.data.basic.BasicNeuralDataSet |
predict()
Generate predictions for the data.
|
org.encog.neural.data.basic.BasicNeuralDataSet |
predict(org.encog.neural.data.basic.BasicNeuralDataSet data)
Evaluate data set using currenr NN
|
org.encog.neural.data.NeuralData |
predict(org.encog.neural.data.NeuralData input)
Evaluate data using currenr NN
|
P0D |
predict(P0D input)
Generate prediction for input data
|
PND |
predict(PND input)
Generate predictions for all input data
|
int |
read(String file,
String name)
Read a neural net from a file.
|
void |
reset()
Reset the weight matrix and the thresholds.
|
String |
save(String file,
String name,
String description)
Save current status of neural net.
|
void |
setData(double[][] input)
Construct a data set from an input
|
void |
setData(double[][] input,
double[][] ideal)
Construct a data set from an input and idea array.
|
void |
setData(PND input)
Set data
|
void |
setData(PND input,
PND ideal)
Set data for training.
|
void |
show()
Show Net in EncodeDocument.
|
void |
showNetwork()
Show a neural net in a frame
|
PND |
standardize(PND input)
Standardize each column.
|
int |
trainBackpropagation(boolean isShow,
int maxEpoch,
double learnRate,
double momentum,
double errorMinEpoch)
Training neural network.Construct a backpropagation trainer.
|
public HNeuralNet()
name
- name for the networkpublic void reset()
public void addFeedForwardLayer(int neuronCount)
neuronCount
- How many neurons in this layerpublic void setData(double[][] input, double[][] ideal)
input
- The input into the neural network for training.ideal
- The ideal output for training.public void setData(double[][] input)
input
- The input into the neural network for training.public void setData(PND input, PND ideal)
input
- input data setideal
- expected resul.public void setData(PND input)
input
- input data setpublic PND standardize(PND input)
input
- PNDpublic org.encog.neural.data.basic.BasicNeuralDataSet getData()
public org.encog.neural.data.NeuralData predict(org.encog.neural.data.NeuralData input)
public P0D predict(P0D input)
input
- input data for predictionspublic org.encog.neural.data.basic.BasicNeuralDataSet predict(org.encog.neural.data.basic.BasicNeuralDataSet data)
public PND predict(PND input)
input
- input data for predictionpublic org.encog.neural.data.basic.BasicNeuralDataSet predict()
public int trainBackpropagation(boolean isShow, int maxEpoch, double learnRate, double momentum, double errorMinEpoch)
isShow
- Show learning on a pop-up plotmaxEpoch
- maximum number of epochslearnRate
- The rate at which the weight matrix will be adjusted based on
learning.momentum
- The influence that previous iteration's training deltas will
have on the current iteration.errorMinEpoch
- min error for epoch.public String save(String file, String name, String description)
file
- File namename
- Name of this neural networkdescription
- descriptionpublic int read(String file, String name)
file
- File namename
- Name of this neural networkpublic org.encog.neural.networks.Network getNetwork()
public void showNetwork()
public org.encog.neural.networks.BasicNetwork editNetwork()
public org.encog.neural.data.basic.BasicNeuralDataSet editData()
public void show()
public ArrayList<Double> getEpochError()
public void doc()
SCaVis 1.0 ©