Package org.joone.engine.extenders

Class Summary
BatchModeExtender This class implements the offline learning, that is, batch mode.
DeltaRuleExtender This abstract class describes the methods needed for a delta rule extender, that is, a class that computes / changes the delta (update weight) value according to some algorithm.
GradientExtender This abstract class describes the methods needed for a gradient extender, that is, a class that computes / changes the gradient value according to some algorithm.
LearnerExtender This abstract class describes the methods that any learner extender must provide.
MomentumExtender This extender implements the momentum term.
OnlineModeExtender This is the default weight updater (online).
RpropExtender This class changes the delta value in such a way that it implements the RPROP algorithm.
SimulatedAnnealingExtender Simulated annealing (SA) refers to the process in which random or thermal noise in a system is systematically decreased over time so as to enhance the system's response.
UpdateWeightExtender This abstract class describes the methods needed for a update weight extender, that is, a class that updates weights (storing) according to some algorithm (e.g.
WeightDecayExtender Weight decay adds a penalty term to the error function.
 



Submit Feedback to pmarrone@users.sourceforge.net