Package org.neuroph.nnet.learning

Provides implementations of specific neural network learning algorithms.

See: Description

Class Summary

Class	Description
AntiHebbianLearning	A variant of Hebbian learning called Anti-Hebbian learning.
BackPropagation	Back Propagation learning rule for Multi Layer Perceptron neural networks.
BinaryDeltaRule	Delta rule learning algorithm for perceptrons with step functions.
BinaryHebbianLearning	Hebbian-like learning algorithm used for Hopfield network.
CompetitiveLearning	Competitive learning rule.
ConvolutionalBackpropagation
DynamicBackPropagation	Backpropagation learning rule with dynamic learning rate and momentum
GeneralizedHebbianLearning	A variant of Hebbian learning called Generalized Hebbian learning.
HopfieldLearning	Learning algorithm for the Hopfield neural network.
InstarLearning	Hebbian-like learning rule for Instar network.
KohonenLearning	Learning algorithm for Kohonen network.
LMS	LMS learning rule for neural networks.
ManhattanPropagation
MomentumBackpropagation	Backpropagation learning rule with momentum.
MomentumBackpropagation.MomentumTrainingData
OjaLearning	Oja learning rule wich is a modification of unsupervised hebbian learning.
OutstarLearning	Hebbian-like learning rule for Outstar network.
PerceptronLearning	Perceptron learning rule for perceptron neural networks.
QuickPropagation
QuickPropagation.QuickPropData
RBFLearning	Learning rule for Radial Basis Function networks.
ResilientPropagation	Resilient Propagation learning rule used for Multi Layer Perceptron neural networks.
SigmoidDeltaRule	Delta rule learning algorithm for perceptrons with sigmoid (or any other diferentiable continuous) functions.
SimulatedAnnealingLearning	This class implements a simulated annealing learning rule for supervised neural networks.
SupervisedHebbianLearning	Supervised hebbian learning rule.
UnsupervisedHebbianLearning	Unsupervised hebbian learning rule.

Package org.neuroph.nnet.learning Description

Provides implementations of specific neural network learning algorithms.