gov.sandia.cognition.learning.algorithm.perceptron.kernel
Class Forgetron.Basic<InputType>

java.lang.Object
  extended by gov.sandia.cognition.util.AbstractCloneableSerializable
      extended by gov.sandia.cognition.learning.algorithm.AbstractBatchAndIncrementalLearner<InputOutputPair<? extends InputType,OutputType>,ResultType>
          extended by gov.sandia.cognition.learning.algorithm.AbstractSupervisedBatchAndIncrementalLearner<InputType,Boolean,DefaultKernelBinaryCategorizer<InputType>>
              extended by gov.sandia.cognition.learning.algorithm.perceptron.kernel.AbstractOnlineKernelBinaryCategorizerLearner<InputType>
                  extended by gov.sandia.cognition.learning.algorithm.perceptron.kernel.AbstractOnlineBudgetedKernelBinaryCategorizerLearner<InputType>
                      extended by gov.sandia.cognition.learning.algorithm.perceptron.kernel.Forgetron.Basic<InputType>
Type Parameters:
InputType - The type of input to learn over. Passed to the kernel function.
All Implemented Interfaces:
BatchAndIncrementalLearner<InputOutputPair<? extends InputType,Boolean>,DefaultKernelBinaryCategorizer<InputType>>, BatchLearner<Collection<? extends InputOutputPair<? extends InputType,Boolean>>,DefaultKernelBinaryCategorizer<InputType>>, IncrementalLearner<InputOutputPair<? extends InputType,Boolean>,DefaultKernelBinaryCategorizer<InputType>>, SupervisedBatchAndIncrementalLearner<InputType,Boolean,DefaultKernelBinaryCategorizer<InputType>>, SupervisedBatchLearner<InputType,Boolean,DefaultKernelBinaryCategorizer<InputType>>, SupervisedIncrementalLearner<InputType,Boolean,DefaultKernelBinaryCategorizer<InputType>>, KernelContainer<InputType>, CloneableSerializable, Serializable, Cloneable
Enclosing class:
Forgetron<InputType>

@PublicationReference(author={"Ofer Dekel","Shai Shalev-Shwartz","Yoram Singer"},
                      title="The Forgetron: A Kernel-based Perceptron on a Budget",
                      year=2008,
                      type=Journal,
                      publication="SIAM Journal on Computing",
                      pages={1342,1372},
                      url="http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.134.7604&rep=rep1&type=pdf",
                      notes="This is the basic version.")
public static class Forgetron.Basic<InputType>
extends AbstractOnlineBudgetedKernelBinaryCategorizerLearner<InputType>

An implementation of the "basic" Forgetron algorithm, which is an online budgeted kernel binary categorizer learner. Note that this appears to be somewhat for illustrative purposes only since it uses the worst-case definition of the shrinking coefficients and thus tends to perform poorly.

Since:
3.3.0
Author:
Justin Basilico
See Also:
Serialized Form

Field Summary
 
Fields inherited from class gov.sandia.cognition.learning.algorithm.perceptron.kernel.AbstractOnlineBudgetedKernelBinaryCategorizerLearner
budget, DEFAULT_BUDGET
 
Fields inherited from class gov.sandia.cognition.learning.algorithm.perceptron.kernel.AbstractOnlineKernelBinaryCategorizerLearner
kernel
 
Constructor Summary
Forgetron.Basic()
          Creates a new Forgetron.Basic with a null kernel and default budget.
Forgetron.Basic(Kernel<? super InputType> kernel, int budget)
          Creates a new Forgetron.Basic with the given kernel and budget.
 
Method Summary
 DefaultKernelBinaryCategorizer<InputType> createInitialLearnedObject()
          Creates a new initial learned object, before any data is given.
 void update(DefaultKernelBinaryCategorizer<InputType> target, InputType input, boolean label)
          Updates the target categorizer based on the given input and its associated output.
 
Methods inherited from class gov.sandia.cognition.learning.algorithm.perceptron.kernel.AbstractOnlineBudgetedKernelBinaryCategorizerLearner
getBudget, setBudget
 
Methods inherited from class gov.sandia.cognition.learning.algorithm.perceptron.kernel.AbstractOnlineKernelBinaryCategorizerLearner
getKernel, setKernel, update
 
Methods inherited from class gov.sandia.cognition.learning.algorithm.AbstractSupervisedBatchAndIncrementalLearner
update
 
Methods inherited from class gov.sandia.cognition.learning.algorithm.AbstractBatchAndIncrementalLearner
clone, learn, learn, update
 
Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 
Methods inherited from interface gov.sandia.cognition.util.CloneableSerializable
clone
 
Methods inherited from interface gov.sandia.cognition.learning.algorithm.BatchAndIncrementalLearner
learn
 
Methods inherited from interface gov.sandia.cognition.learning.algorithm.BatchLearner
learn
 
Methods inherited from interface gov.sandia.cognition.learning.algorithm.IncrementalLearner
update
 

Constructor Detail

Forgetron.Basic

public Forgetron.Basic()
Creates a new Forgetron.Basic with a null kernel and default budget.


Forgetron.Basic

public Forgetron.Basic(Kernel<? super InputType> kernel,
                       int budget)
Creates a new Forgetron.Basic with the given kernel and budget.

Parameters:
kernel - The kernel to use.
budget - The budget for the maximum number of supports.
Method Detail

createInitialLearnedObject

public DefaultKernelBinaryCategorizer<InputType> createInitialLearnedObject()
Description copied from interface: IncrementalLearner
Creates a new initial learned object, before any data is given.

Specified by:
createInitialLearnedObject in interface IncrementalLearner<InputOutputPair<? extends InputType,Boolean>,DefaultKernelBinaryCategorizer<InputType>>
Overrides:
createInitialLearnedObject in class AbstractOnlineKernelBinaryCategorizerLearner<InputType>
Returns:
The initial learned object.

update

public void update(DefaultKernelBinaryCategorizer<InputType> target,
                   InputType input,
                   boolean label)
Description copied from class: AbstractOnlineKernelBinaryCategorizerLearner
Updates the target categorizer based on the given input and its associated output.

Specified by:
update in class AbstractOnlineKernelBinaryCategorizerLearner<InputType>
Parameters:
target - The target categorizer to update.
input - The input value to learn from.
label - The output value associated with the input.