Modifier and Type | Class and Description |
---|---|
class |
ActivationBiPolar
BiPolar activation function.
|
class |
ActivationBipolarSteepenedSigmoid
The bipolar sigmoid activation function is like the regular sigmoid activation function,
except Bipolar sigmoid activation function.
|
class |
ActivationClippedLinear
Linear activation function that bounds the output to [-1,+1].
|
class |
ActivationCompetitive
An activation function that only allows a specified number, usually one, of
the out-bound connection to win.
|
class |
ActivationElliott
Computationally efficient alternative to ActivationSigmoid.
|
class |
ActivationElliottSymmetric
Computationally efficient alternative to ActivationTANH.
|
class |
ActivationGaussian
An activation function based on the Gaussian function.
|
class |
ActivationLinear
The Linear layer is really not an activation function at all.
|
class |
ActivationLOG
An activation function based on the logarithm function.
|
class |
ActivationRamp
A ramp activation function.
|
class |
ActivationSigmoid
The sigmoid activation function takes on a sigmoidal shape.
|
class |
ActivationSIN
An activation function based on the sin function, with a double period.
|
class |
ActivationSoftMax
The softmax activation function.
|
class |
ActivationSteepenedSigmoid
The Steepened Sigmoid is an activation function typically used with NEAT.
|
class |
ActivationStep
The step activation function is a very simple activation function.
|
class |
ActivationTANH
The hyperbolic tangent activation function takes the curved shape of the
hyperbolic tangent.
|
Modifier and Type | Method and Description |
---|---|
ActivationFunction |
ActivationCompetitive.clone() |
ActivationFunction |
ActivationElliottSymmetric.clone() |
ActivationFunction |
ActivationGaussian.clone() |
ActivationFunction |
ActivationBiPolar.clone() |
ActivationFunction |
ActivationTANH.clone() |
ActivationFunction |
ActivationClippedLinear.clone() |
ActivationFunction |
ActivationSoftMax.clone() |
ActivationFunction |
ActivationSIN.clone() |
ActivationFunction |
ActivationElliott.clone() |
ActivationFunction |
ActivationLOG.clone() |
ActivationFunction |
ActivationFunction.clone() |
ActivationFunction |
ActivationSteepenedSigmoid.clone() |
ActivationFunction |
ActivationLinear.clone() |
ActivationFunction |
ActivationStep.clone() |
ActivationFunction |
ActivationSigmoid.clone() |
ActivationFunction |
ActivationRamp.clone()
Clone the object.
|
ActivationFunction |
ActivationBipolarSteepenedSigmoid.clone() |
Modifier and Type | Method and Description |
---|---|
void |
MultiLayerPerceptronFactory.setParameters(Collection<Integer> layers,
ActivationFunction activation) |
Constructor and Description |
---|
MarketDataDescription(TickerSymbol ticker,
MarketDataType dataType,
TemporalDataDescription.Type type,
ActivationFunction activationFunction,
boolean input,
boolean predict)
Construct a MarketDataDescription item.
|
Modifier and Type | Method and Description |
---|---|
ActivationFunction |
TemporalDataDescription.getActivationFunction() |
Constructor and Description |
---|
TemporalDataDescription(ActivationFunction activationFunction,
double low,
double high,
TemporalDataDescription.Type type,
boolean input,
boolean predict)
Construct a data description item.
|
TemporalDataDescription(ActivationFunction activationFunction,
TemporalDataDescription.Type type,
boolean input,
boolean predict)
Construct a data description with an activation function, but no range.
|
Modifier and Type | Method and Description |
---|---|
ActivationFunction |
MLActivationFactory.create(String fn) |
Modifier and Type | Method and Description |
---|---|
ActivationFunction |
FlatLayer.getActivation() |
ActivationFunction[] |
FlatNetwork.getActivationFunctions() |
Modifier and Type | Method and Description |
---|---|
void |
FlatLayer.setActivation(ActivationFunction activation) |
void |
FlatNetwork.setActivationFunctions(ActivationFunction[] af)
Set the activation functions.
|
Constructor and Description |
---|
FlatLayer(ActivationFunction activation,
int count,
double biasActivation)
Construct a flat layer.
|
Modifier and Type | Method and Description |
---|---|
ActivationFunction |
InputSummation.getActivationFunction() |
Modifier and Type | Method and Description |
---|---|
void |
FreeformNetwork.ConnectLayers(FreeformLayer source,
FreeformLayer target,
ActivationFunction theActivationFunction)
Connect two layers, assume bias activation of 1.0 and non-recurrent
connection.
|
void |
FreeformNetwork.connectLayers(FreeformLayer source,
FreeformLayer target,
ActivationFunction theActivationFunction,
double biasActivation,
boolean isRecurrent)
Connect two layers.
|
static FreeformNetwork |
FreeformNetwork.createElman(int input,
int hidden1,
int output,
ActivationFunction af)
Construct an Elmann recurrent neural network.
|
static FreeformNetwork |
FreeformNetwork.createFeedforward(int input,
int hidden1,
int hidden2,
int output,
ActivationFunction af)
Create a feedforward freeform neural network.
|
Modifier and Type | Method and Description |
---|---|
ActivationFunction |
BasicActivationSummation.getActivationFunction() |
Modifier and Type | Method and Description |
---|---|
InputSummation |
BasicActivationSummationFactory.factor(ActivationFunction theActivationFunction)
Create a new input summation.
|
void |
BasicActivationSummation.setActivationFunction(ActivationFunction activationFunction)
Set the activation function.
|
Constructor and Description |
---|
BasicActivationSummation(ActivationFunction theActivationFunction)
Construct the activation summation.
|
Modifier and Type | Method and Description |
---|---|
InputSummation |
InputSummationFactory.factor(ActivationFunction activationFunction)
Create a new input summation.
|
Modifier and Type | Method and Description |
---|---|
static void |
HyperNEATGenome.buildCPPNActivationFunctions(ChooseObject<ActivationFunction> activationFunctions)
Build the CPPN activation functions.
|
Modifier and Type | Method and Description |
---|---|
ActivationFunction[] |
NEATNetwork.getActivationFunctions() |
Modifier and Type | Method and Description |
---|---|
ChooseObject<ActivationFunction> |
NEATPopulation.getActivationFunctions() |
Modifier and Type | Method and Description |
---|---|
void |
NEATPopulation.setNEATActivationFunction(ActivationFunction af)
Specify to use a single activation function.
|
Constructor and Description |
---|
NEATNetwork(int inputNeuronCount,
int outputNeuronCount,
List<NEATLink> connectionArray,
ActivationFunction[] theActivationFunctions)
Construct a NEAT network.
|
Modifier and Type | Method and Description |
---|---|
ActivationFunction |
NEATNeuronGene.getActivationFunction() |
Modifier and Type | Method and Description |
---|---|
void |
NEATNeuronGene.setActivationFunction(ActivationFunction activationFunction) |
Constructor and Description |
---|
NEATNeuronGene(NEATNeuronType type,
ActivationFunction theActivationFunction,
long id,
long innovationID)
Construct a neuron gene.
|
Modifier and Type | Method and Description |
---|---|
ActivationFunction |
BasicNetwork.getActivation(int layer)
Get the activation function for the specified layer.
|
Modifier and Type | Method and Description |
---|---|
ActivationFunction |
Layer.getActivationFunction() |
ActivationFunction |
BasicLayer.getActivationFunction() |
Modifier and Type | Method and Description |
---|---|
void |
Layer.setActivation(ActivationFunction activation)
Set the activation function.
|
Constructor and Description |
---|
BasicLayer(ActivationFunction activationFunction,
boolean hasBias,
int neuronCount)
Construct this layer with a non-default activation function, also
determine if a bias is desired or not.
|
Modifier and Type | Method and Description |
---|---|
ActivationFunction |
FeedForwardPattern.getActivationOutput() |
Modifier and Type | Method and Description |
---|---|
void |
NeuralNetworkPattern.setActivationFunction(ActivationFunction activation)
Set the activation function to be used for all created layers that allow
an activation function to be specified.
|
void |
ART1Pattern.setActivationFunction(ActivationFunction activation)
This method will throw an error, you can't set the activation function
for an ART1.
|
void |
BAMPattern.setActivationFunction(ActivationFunction activation)
Not used, the BAM uses a bipoloar activation function.
|
void |
ElmanPattern.setActivationFunction(ActivationFunction activation)
Set the activation function to use on each of the layers.
|
void |
JordanPattern.setActivationFunction(ActivationFunction activation)
Set the activation function to use on each of the layers.
|
void |
RadialBasisPattern.setActivationFunction(ActivationFunction activation)
Set the activation function, this is an error.
|
void |
BoltzmannPattern.setActivationFunction(ActivationFunction activation)
Not used, will throw an exception.
|
void |
ADALINEPattern.setActivationFunction(ActivationFunction activation)
Not used, ADALINE does not use custom activation functions.
|
void |
FeedForwardPattern.setActivationFunction(ActivationFunction activation)
Set the activation function to use on each of the layers.
|
void |
SVMPattern.setActivationFunction(ActivationFunction activation)
Not used, the BAM uses a bipoloar activation function.
|
void |
SOMPattern.setActivationFunction(ActivationFunction activation)
Set the activation function.
|
void |
CPNPattern.setActivationFunction(ActivationFunction activation)
This method will throw an error.
|
void |
HopfieldPattern.setActivationFunction(ActivationFunction activation)
Set the activation function to use.
|
void |
PNNPattern.setActivationFunction(ActivationFunction activation)
Set the activation function.
|
void |
FeedForwardPattern.setActivationOutput(ActivationFunction activationOutput) |
Modifier and Type | Method and Description |
---|---|
static ActivationFunction |
EncogFileSection.parseActivationFunction(Map<String,String> params,
String name)
Parse an activation function from a string.
|
static ActivationFunction |
EncogFileSection.parseActivationFunction(String value)
Parse an activation function from a value.
|
Modifier and Type | Method and Description |
---|---|
void |
EncogWriteHelper.addColumn(ActivationFunction act) |
void |
EncogWriteHelper.writeProperty(String name,
ActivationFunction act)
Write a property as an activation function.
|
Modifier and Type | Method and Description |
---|---|
ActivationFunction |
EncogPluginService1.createActivationFunction(String name)
Create an activation function.
|
Modifier and Type | Method and Description |
---|---|
ActivationFunction |
SystemActivationPlugin.createActivationFunction(String fn)
Create an activation function.
|
ActivationFunction |
SystemTrainingPlugin.createActivationFunction(String name)
This plugin does not support activation functions, so it will
always return null.
|
ActivationFunction |
SystemMethodsPlugin.createActivationFunction(String name)
Create an activation function.
|
Modifier and Type | Method and Description |
---|---|
static String |
ActivationUtil.generateActivationFactory(String name,
ActivationFunction af) |
Copyright © 2014. All Rights Reserved.