Class ResilientBackpropagation
- java.lang.Object
-
- libai.nn.supervised.backpropagation.StandardBackpropagation
-
- libai.nn.supervised.backpropagation.ResilientBackpropagation
-
- All Implemented Interfaces:
Backpropagation
public class ResilientBackpropagation extends StandardBackpropagation
Created by kronenthaler on 18/01/2017.
-
-
Field Summary
Fields Modifier and Type Field Description protected double
initialUpdate
protected double
maxUpdate
protected double
minUpdate
protected double
nMinus
protected double
nPlus
-
Constructor Summary
Constructors Constructor Description ResilientBackpropagation()
ResilientBackpropagation(double nPlus, double nMinus, double minUpdate, double maxUpdate, double initialUpdate)
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description void
train(Column[] patterns, Column[] answers, double alpha, int epochs, int offset, int length, double minerror)
Trains a neural network using the backpropagation implementaion.-
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
-
Methods inherited from class libai.nn.supervised.backpropagation.StandardBackpropagation
initialize
-
-
-
-
Method Detail
-
train
public void train(Column[] patterns, Column[] answers, double alpha, int epochs, int offset, int length, double minerror)
Description copied from interface:Backpropagation
Trains a neural network using the backpropagation implementaion.- Specified by:
train
in interfaceBackpropagation
- Overrides:
train
in classStandardBackpropagation
-
-