public class SigmoidalRule extends AbstractSigmoidalRule
NeuronUpdateRule.InputType
addNoise, bias, DEFAULT_LOWER_BOUND, DEFAULT_SQUASHING_FUNCTION, DEFAULT_UPPER_BOUND, lowerBound, noiseGenerator, sFunction, slope, upperBound
DEFAULT_INCREMENT, increment, inputType
Constructor and Description |
---|
SigmoidalRule()
Default sigmoidal.
|
SigmoidalRule(SquashingFunction sFunction)
Construct a sigmoid update with a specified implementation.
|
Modifier and Type | Method and Description |
---|---|
void |
contextualDecrement(Neuron n)
Decrement a neuron by increment, respecting neuron specific constraints.
|
void |
contextualIncrement(Neuron n)
Increment a neuron by increment, respecting neuron specific constraints.
|
SigmoidalRule |
deepCopy()
Returns a deep copy of the update rule.
|
double |
getDerivative(double val)
The inverse of the activation function.
|
java.lang.String |
getDescription()
Returns a brief description of this update rule.
|
Network.TimeType |
getTimeType()
Returns the type of time update (discrete or continuous) associated with
this neuron.
|
void |
update(Neuron neuron)
Apply the update rule.
|
getAddNoise, getBias, getInverse, getLowerBound, getNoiseGenerator, getSlope, getSquashFunctionType, getUpperBound, setAddNoise, setBias, setLowerBound, setNoiseGenerator, setSlope, setSquashFunctionType, setUpperBound
clear, decrementActivation, getDefaultIncrement, getGraphicalLowerBound, getGraphicalUpperBound, getIncrement, getInputType, getRandomValue, getToolTipText, incrementActivation, isSkipsSynapticUpdates, isSpikingNeuron, setIncrement, setInputType
public SigmoidalRule()
public SigmoidalRule(SquashingFunction sFunction)
sFunction
- the squashing function implementation to use.public Network.TimeType getTimeType()
getTimeType
in class NeuronUpdateRule
public void update(Neuron neuron)
update
in class NeuronUpdateRule
neuron
- parent neuronpublic void contextualIncrement(Neuron n)
NeuronUpdateRule
contextualIncrement
in class NeuronUpdateRule
n
- neuron to be incrementedpublic void contextualDecrement(Neuron n)
NeuronUpdateRule
contextualDecrement
in class NeuronUpdateRule
n
- neuronpublic double getDerivative(double val)
val
- the value being sent through the neuron's derivativepublic SigmoidalRule deepCopy()
deepCopy
in class NeuronUpdateRule
public java.lang.String getDescription()
NeuronUpdateRule
getDescription
in class NeuronUpdateRule