@PublicationReference(author={"Shai Shalev-Shwartz","Yoram Singer"}, title="A New Perspective on an Old Perceptron Algorithm", year=2005, type=Conference, publication="Conference on Learning Theory", pages={815,824}, url="http://www.springerlink.com/index/hr4hrbyajy0y8a7l.pdf") public class Ballseptron extends AbstractKernelizableBinaryCategorizerOnlineLearner
Modifier and Type | Field and Description |
---|---|
static double |
DEFAULT_RADIUS
The default radius is 0.1.
|
protected double |
radius
The radius enforced by the algorithm.
|
vectorFactory
Constructor and Description |
---|
Ballseptron()
Creates a new
Ballseptron with default parameters. |
Ballseptron(double radius)
Creates a new
Ballseptron with the given radius. |
Modifier and Type | Method and Description |
---|---|
double |
getRadius()
Gets the radius parameter.
|
void |
setRadius(double radius)
Sets the radius parameter.
|
<InputType> |
update(DefaultKernelBinaryCategorizer<InputType> target,
InputType input,
boolean label)
Performs a kernel-based incremental update step on the given object
using the given supervised data.
|
void |
update(LinearBinaryCategorizer target,
Vector input,
boolean label)
The
update method updates an object of ResultType using
the given a new supervised input-output pair, using some form of
"learning" algorithm. |
createInitialLearnedObject, createKernelLearner, learn, update, update, update
createInitialLearnedObject, getVectorFactory, setVectorFactory, update
update
clone, learn, learn, update
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
update
learn
learn
createInitialLearnedObject, update, update
clone
public static final double DEFAULT_RADIUS
protected double radius
public Ballseptron()
Ballseptron
with default parameters.public Ballseptron(double radius)
Ballseptron
with the given radius.radius
- The radius.public void update(LinearBinaryCategorizer target, Vector input, boolean label)
AbstractOnlineLinearBinaryCategorizerLearner
update
method updates an object of ResultType
using
the given a new supervised input-output pair, using some form of
"learning" algorithm.update
in class AbstractOnlineLinearBinaryCategorizerLearner
target
- The object to update.input
- The supervised input vector to learn from.label
- The supervised output label to learn from.public <InputType> void update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean label)
KernelizableBinaryCategorizerOnlineLearner
InputType
- The input type for supervised learning. Will be passed to the
kernel function.target
- The target object to update.input
- The supervised input value.label
- The supervised output value (label).public double getRadius()
public void setRadius(double radius)
radius
- The radius parameter. Must be positive.