Uses of Class
org.joone.util.MonitorPlugin

Packages that use MonitorPlugin
org.joone.engine   
org.joone.engine.listeners   
org.joone.util   
 

Uses of MonitorPlugin in org.joone.engine
 

Subclasses of MonitorPlugin in org.joone.engine
 class EKFFFNLearnerPlugin
          A plugin listener that implements the EKFFFN learner used to train feed forward neural networks.
 class EKFRNNLearnerPlugin
          A plugin listener that implements the EKF learner, based on "Some observations on the use of the extended Kalman filter as a recurrent network learning algorithm" by Williams (1992) in order to train a network.
 class RTRLLearnerPlugin
          A plugin listener that applies the RTRL algorithm to a network.
 

Uses of MonitorPlugin in org.joone.engine.listeners
 

Subclasses of MonitorPlugin in org.joone.engine.listeners
 class ConvergenceObserver
          Abstract class for all convergence observer.
 class DeltaBasedConvergenceObserver
          This observer observes if the network has convergenced based on the size of the weight updates (deltas).
 class ErrorBasedConvergenceObserver
          This observer observes if the network has convergenced based on the sequence of training errors.
 class ErrorBasedTerminator
          Stops a network whenever the training error of the network falls below a certain value.
 

Uses of MonitorPlugin in org.joone.util
 

Subclasses of MonitorPlugin in org.joone.util
 class DynamicAnnealing
          This plugin controls the change of the learning rate based on the difference between the last two global error (E) values: if E(t) > E(t-1) then LR = LR * (1 - step/100) Note: step/100 because step is inserted as a % value from the user if E(t) <= E(t-1) then LR is unchanged
 class GroovyMacroPlugin
           
 class LinearAnnealing
          This plugin changes linearly the values of the learning rate and of the momentum parameters.
 class MacroPlugin
           
 class SnapshotPlugin
          A SnapshotPlugin manages the generation of snapshots of the network's state at regular intervals during its activity.
 class SnapshotRecorder
          A SnapshotRecorder serves to create and record snapshots of a neural network in a file as a serie of serialized objects graphs.
 class WeightWriterPlugin
          A class that can be used to write weight values during training to a file in gnuplot format.
 



Submit Feedback to pmarrone@users.sourceforge.net