NearNeural

Class SigmoidThresholdModel

java.lang.Object

NearNeural.WeightedThresholdModel

NearNeural.SigmoidThresholdModel

All Implemented Interfaces:

ThresholdingAlgorithm

public class SigmoidThresholdModel
extends WeightedThresholdModel
implements ThresholdingAlgorithm

Represents a thresholding algorithm based on the sigmoid function.

Version:

0.2

Author:

Stephen Wattam

Field Summary

Fields inherited from class NearNeural.WeightedThresholdModel

k

Constructor Summary

Constructors

Constructor and Description
SigmoidThresholdModel(double p_k) Creates a new thresholding function with the given 'harshness'.

Method Summary

Methods

Modifier and Type	Method and Description
double	differentialValue(Edge[] edges) Defined in ThresholdingAlgorithm, returns differential of current value.
boolean	validateInput(double input) Validates input values.
double	value(Edge[] edges) Calculates Neuron value from all Edges and their source Neurons.

Methods inherited from class NearNeural.WeightedThresholdModel

getK, setK

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

SigmoidThresholdModel

public SigmoidThresholdModel(double p_k)

Creates a new thresholding function with the given 'harshness'.

Parameters:

p_k - the steepness of the dropoff

Method Detail

value

public double value(Edge[] edges)

Calculates Neuron value from all Edges and their source Neurons.

Specified by:

value in interface ThresholdingAlgorithm

Parameters:

edges - All of the edges leading into this neuron

Returns:

This Neuron's value

validateInput

public boolean validateInput(double input)

Validates input values.

Specified by:

validateInput in interface ThresholdingAlgorithm

Parameters:

input - The input value to check. This does not have to conform to strict asymptotic rules as edge weights are applied.

Returns:

True if the input is valid, false if not.

differentialValue

public double differentialValue(Edge[] edges)

Defined in ThresholdingAlgorithm, returns differential of current value.

Specified by:

differentialValue in interface ThresholdingAlgorithm

Parameters:

edges - All edges connected to the neuron

Returns:

The differential of the value