gov.sandia.cognition.learning.function.scalar

Class HardSigmoidFunction

java.lang.Object

gov.sandia.cognition.util.AbstractCloneableSerializable

gov.sandia.cognition.math.AbstractScalarFunction<java.lang.Double>

gov.sandia.cognition.math.AbstractUnivariateScalarFunction

gov.sandia.cognition.math.AbstractDifferentiableUnivariateScalarFunction

gov.sandia.cognition.learning.function.scalar.HardSigmoidFunction

All Implemented Interfaces:

Evaluator<java.lang.Double,java.lang.Double>, DifferentiableEvaluator<java.lang.Double,java.lang.Double,java.lang.Double>, DifferentiableUnivariateScalarFunction, ScalarFunction<java.lang.Double>, UnivariateScalarFunction, CloneableSerializable, java.io.Serializable, java.lang.Cloneable

public class HardSigmoidFunction
extends AbstractDifferentiableUnivariateScalarFunction

A hard sigmoid function, which is an approximation of a logistic sigmoid whose output is between 0 and 1. The function maps values between -2.5 and 2.5 linearly between 0 and 1 and for values outside that range it is capped. Unlike the soft sigmoid it actually ends up producing values of 0 and 1 for inputs outside of that range, where it is saturated. The functional form is: f(x) = min(1.0, max(0.0, 0.2 * x + 0.5))

Since:

4.0.0

Author:

Justin Basilico

See Also:

SigmoidFunction, Serialized Form

Constructor Summary

Constructors

Constructor and Description
HardSigmoidFunction() Creates a new HardSigmoidFunction.

Method Summary

Modifier and Type	Method and Description
HardSigmoidFunction	clone() This makes public the clone method on the Object class and removes the exception that it throws.
double	differentiate(double input) Differentiates the output of the function about the given input
double	evaluate(double input) Produces a double output for the given double input
static double	hardSigmoid(double input) Computes the hard sigmoid function.

Methods inherited from class java.lang.Object

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

Methods inherited from interface gov.sandia.cognition.math.DifferentiableUnivariateScalarFunction

differentiate

Methods inherited from interface gov.sandia.cognition.math.UnivariateScalarFunction

evaluate, evaluateAsDouble

Constructor Detail

HardSigmoidFunction

public HardSigmoidFunction()

Creates a new HardSigmoidFunction.

Method Detail

clone

public HardSigmoidFunction clone()

Description copied from class: AbstractCloneableSerializable

This makes public the clone method on the Object class and removes the exception that it throws. Its default behavior is to automatically create a clone of the exact type of object that the clone is called on and to copy all primitives but to keep all references, which means it is a shallow copy. Extensions of this class may want to override this method (but call super.clone() to implement a "smart copy". That is, to target the most common use case for creating a copy of the object. Because of the default behavior being a shallow copy, extending classes only need to handle fields that need to have a deeper copy (or those that need to be reset). Some of the methods in ObjectUtil may be helpful in implementing a custom clone method. Note: The contract of this method is that you must use super.clone() as the basis for your implementation.

Specified by:

clone in interface CloneableSerializable

Overrides:

clone in class AbstractCloneableSerializable

Returns:

A clone of this object.

evaluate

public double evaluate(double input)

Description copied from interface: UnivariateScalarFunction

Produces a double output for the given double input

Parameters:

input - Input to the Evaluator

Returns:

output at the given input

differentiate

public double differentiate(double input)

Description copied from interface: DifferentiableUnivariateScalarFunction

Differentiates the output of the function about the given input

Parameters:

input - Input about which to compute the derivative of the function output

Returns:

Derivative of the output with respect to the input

hardSigmoid

public static double hardSigmoid(double input)

Computes the hard sigmoid function. The functional form is: f(x) = min(1.0, max(0.0, 0.2 * x + 0.5))

Parameters:

input - The input value to apply the hard sigmoid to.

Returns:

The output, which is between 0.0 and 1.0. If NaN is given, NaN will be returned.