NearNeural

Class LinearThresholdModel

java.lang.Object

NearNeural.WeightedThresholdModel

NearNeural.LinearThresholdModel

All Implemented Interfaces:

ThresholdingAlgorithm

public class LinearThresholdModel
extends WeightedThresholdModel
implements ThresholdingAlgorithm

A threshold which is linear.This method may not work at all with some backpropagation methods

Where x is k*sum(edge_weight*neuron_value) for all input edges. Differential is, of course, k

Version:

0.3

Author:

Stephen Wattam

Field Summary

Fields inherited from class NearNeural.WeightedThresholdModel

k

Constructor Summary

Constructors

Constructor and Description
LinearThresholdModel(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) Returns the differential of the thresholding function.
boolean	validateInput(double input) Validates input against the applicable range for this thresholding algorithm.
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

LinearThresholdModel

public LinearThresholdModel(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 against the applicable range for this thresholding algorithm.

Specified by:

validateInput in interface ThresholdingAlgorithm

Parameters:

input - The value to check

Returns:

True if the value is applicable to run though without error

differentialValue

public double differentialValue(Edge[] edges)

Returns the differential of the thresholding function.

Specified by:

differentialValue in interface ThresholdingAlgorithm

Parameters:

edges - The edges that comprise the links this neuron has.

Returns:

The differential of the value