Package | Description |
---|---|
org.encog.neural.pattern | |
org.encog.neural.prune |
Modifier and Type | Class and Description |
---|---|
class |
ADALINEPattern
Construct an ADALINE neural network.
|
class |
ART1Pattern
Pattern to create an ART-1 neural network.
|
class |
BAMPattern
Construct a Bidirectional Access Memory (BAM) neural network.
|
class |
BoltzmannPattern
Pattern to create a Boltzmann machine.
|
class |
CPNPattern
Pattern that creates a CPN neural network.
|
class |
ElmanPattern
This class is used to generate an Elman style recurrent neural network.
|
class |
FeedForwardPattern
Used to create feedforward neural networks.
|
class |
HopfieldPattern
Create a Hopfield pattern.
|
class |
JordanPattern
This class is used to generate an Jordan style recurrent neural network.
|
class |
PNNPattern
Pattern to create a PNN.
|
class |
RadialBasisPattern
A radial basis function (RBF) network uses several radial basis functions to
provide a more dynamic hidden layer activation function than many other types
of neural network.
|
class |
SOMPattern
A self organizing map is a neural network pattern with an input and output
layer.
|
class |
SVMPattern
A pattern to create support vector machines.
|
Modifier and Type | Method and Description |
---|---|
NeuralNetworkPattern |
PruneIncremental.getPattern() |
Constructor and Description |
---|
PruneIncremental(MLDataSet training,
NeuralNetworkPattern pattern,
int iterations,
int weightTries,
int numTopResults,
StatusReportable report)
Construct an object to determine the optimal number of hidden layers and
neurons for the specified training data and pattern.
|
Copyright © 2014. All Rights Reserved.