org.encog.ml.svm
Class SVM

java.lang.Object
  org.encog.ml.BasicML
      org.encog.ml.svm.SVM

All Implemented Interfaces:

Serializable, MLClassification, MLError, MLInput, MLInputOutput, MLMethod, MLOutput, MLProperties, MLRegression

public class SVM
extends BasicML
implements MLRegression, MLClassification, MLError

This is a network that is backed by one or more Support Vector Machines (SVM). It is designed to function very similarly to an Encog neural network, and is largely interchangeable with an Encog neural network. The support vector machine supports several types. Regression is used when you want the network to predict a value, given the input. Function approximation is a good example of regression. Classification is used when you want the SVM to group the input data into one or more classes. Support Vector Machines typically have a single output. Neural networks can have multiple output neurons. To get around this issue, this class will create multiple SVM's if there is more than one output specified. Because a SVM is trained quite differently from a neural network, none of the neural network training classes will work. This class must be trained using SVMTrain.

See Also:

Serialized Form

Field Summary

static int	DEFAULT_C The default C.
static int	DEFAULT_CACHE_SIZE The default cache size.
static int	DEFAULT_COEF0 The default COEF0.
static int	DEFAULT_DEGREE The default degree.
static double	DEFAULT_EPS The default EPS.
static double	DEFAULT_NU The default NU.
static double	DEFAULT_P The default P.

Constructor Summary

SVM()
Construct the SVM.

SVM(int theInputCount, boolean regression)
Construct an SVM network.

SVM(int theInputCount, SVMType svmType, KernelType kernelType)
Construct a SVM network.

SVM(svm_model theModel)
Construct a SVM from a model.

Method Summary

double	calculateError(MLDataSet data) Calculate the error for this SVM.
int	classify(MLData input) Classify the input into a group.
MLData	compute(MLData input) Compute the output for the given input.
int	getInputCount()
KernelType	getKernelType()
svm_model	getModel()
int	getOutputCount()
svm_parameter	getParams()
SVMType	getSVMType()
svm_node[]	makeSparse(MLData data) Convert regular Encog MLData into the "sparse" data needed by an SVM.
void	setInputCount(int i) Set the input count.
void	setModel(svm_model theModel) Set the model.
void	updateProperties() Not needed, no properties to update.

Methods inherited from class org.encog.ml.BasicML

getProperties, getPropertyDouble, getPropertyLong, getPropertyString, setProperty, setProperty, setProperty

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

DEFAULT_DEGREE

public static final int DEFAULT_DEGREE

The default degree.

See Also:

Constant Field Values

DEFAULT_COEF0

public static final int DEFAULT_COEF0

The default COEF0.

See Also:

Constant Field Values

DEFAULT_NU

public static final double DEFAULT_NU

The default NU.

See Also:

Constant Field Values

DEFAULT_CACHE_SIZE

public static final int DEFAULT_CACHE_SIZE

The default cache size.

See Also:

Constant Field Values

DEFAULT_C

public static final int DEFAULT_C

The default C.

See Also:

Constant Field Values

DEFAULT_EPS

public static final double DEFAULT_EPS

The default EPS.

See Also:

Constant Field Values

DEFAULT_P

public static final double DEFAULT_P

The default P.

See Also:

Constant Field Values

Constructor Detail

SVM

public SVM()

Construct the SVM.

SVM

public SVM(int theInputCount,
           boolean regression)

Construct an SVM network. For regression it will use an epsilon support vector. Both types will use an RBF kernel.

Parameters:

theInputCount - The input count.

regression - True if this network is used for regression.

SVM

public SVM(int theInputCount,
           SVMType svmType,
           KernelType kernelType)

Construct a SVM network.

Parameters:

theInputCount - The input count.

svmType - The type of SVM.

kernelType - The SVM kernal type.

SVM

public SVM(svm_model theModel)

Construct a SVM from a model.

Parameters:

theModel - The model.

Method Detail

calculateError

public double calculateError(MLDataSet data)

Calculate the error for this SVM.

Specified by:

calculateError in interface MLError

Parameters:

data - The training set.

Returns:

The error percentage.

classify

public int classify(MLData input)

Classify the input into a group.

Specified by:

classify in interface MLClassification

Parameters:

input - The input data to classify.

Returns:

The group that the data was classified into.

compute

public MLData compute(MLData input)

Compute the output for the given input.

Specified by:

compute in interface MLRegression

Parameters:

input - The input to the SVM.

Returns:

The results from the SVM.

getInputCount

public int getInputCount()

Specified by:

getInputCount in interface MLInput

Returns:

The input count.

getKernelType

public KernelType getKernelType()

Returns:

The kernel type.

getModel

public svm_model getModel()

Returns:

The SVM models for each output.

getOutputCount

public int getOutputCount()

Specified by:

getOutputCount in interface MLOutput

Returns:

For a SVM, the output count is always one.

getParams

public final svm_parameter getParams()

Returns:

The SVM params for each of the outputs.

getSVMType

public SVMType getSVMType()

Returns:

The SVM type.

makeSparse

public svm_node[] makeSparse(MLData data)

Convert regular Encog MLData into the "sparse" data needed by an SVM.

Parameters:

data - The data to convert.

Returns:

The SVM sparse data.

setInputCount

public void setInputCount(int i)

Set the input count.

Parameters:

i - The new input count.

setModel

public void setModel(svm_model theModel)

Set the model.

Parameters:

theModel - The model.

updateProperties

public void updateProperties()

Not needed, no properties to update.

Specified by:

updateProperties in interface MLProperties

Specified by:

updateProperties in class BasicML