gov.sandia.cognition.learning.function.scalar

Class RectifiedLinearFunction

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.RectifiedLinearFunction

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

@PublicationReference(author="Wikipedia",
                      title="Rectifier",
                      type=WebPage,
                      year=2014,
                      url="http://en.wikipedia.org/wiki/Rectifier_(neural_networks)")
public class RectifiedLinearFunction
extends AbstractDifferentiableUnivariateScalarFunction

A rectified linear unit, which is the maximum of its input or 0. It is typically used as an activation function in a neural network. Generally, its derivative is 1 for values larger than 0 and 0 for those smaller than 0. Although the derivative is ill-defined at 0 itself, the implementation treats the derivative at 0 as 0. It is typically useful for handling the vanishing gradient problem.

Since:

3.4.0

Author:

Justin Basilico

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
RectifiedLinearFunction() Creates a new RectifiedLinearFunction.

Method Summary

Modifier and Type	Method and Description
RectifiedLinearFunction	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

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

RectifiedLinearFunction

public RectifiedLinearFunction()

Creates a new RectifiedLinearFunction.

Method Detail

clone

public RectifiedLinearFunction 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