LinearFunction Class

Linear activation function.

Inheritance Hierarchy

SystemObject
Accord.NeuroLinearFunction

Namespace: Accord.Neuro
Assembly: Accord.Neuro (in Accord.Neuro.dll) Version: 3.8.0

Syntax

Copy

[SerializableAttribute]
public class LinearFunction : IActivationFunction

<SerializableAttribute>
Public Class LinearFunction
	Implements IActivationFunction

Request Example View Source

The LinearFunction type exposes the following members.

Constructors

	Name	Description
	LinearFunction	Initializes a new instance of the LinearFunction class.
	LinearFunction(Double)	Initializes a new instance of the LinearFunction class.
	LinearFunction(DoubleRange)	Initializes a new instance of the LinearFunction class.
	LinearFunction(Double, DoubleRange)	Initializes a new instance of the LinearFunction class.

Top

Properties

	Name	Description
	Alpha	Linear slope value.
	Range	Function output range.

Top

Methods

	Name	Description
	Derivative	Calculates function derivative.
	Derivative2	Calculates function derivative.
	Equals	Determines whether the specified object is equal to the current object. (Inherited from Object.)
	Finalize	Allows an object to try to free resources and perform other cleanup operations before it is reclaimed by garbage collection. (Inherited from Object.)
	Function	Calculates function value.
	GetHashCode	Serves as the default hash function. (Inherited from Object.)
	GetType	Gets the Type of the current instance. (Inherited from Object.)
	MemberwiseClone	Creates a shallow copy of the current Object. (Inherited from Object.)
	ToString	Returns a string that represents the current object. (Inherited from Object.)

Top

Extension Methods

	Name	Description
	HasMethod	Checks whether an object implements a method with the given name. (Defined by ExtensionMethods.)
	IsEqual	Compares two objects for equality, performing an elementwise comparison if the elements are vectors or matrices. (Defined by Matrix.)
	To(Type)	Overloaded. Converts an object into another type, irrespective of whether the conversion can be done at compile time or not. This can be used to convert generic types to numeric types during runtime. (Defined by ExtensionMethods.)
	ToT	Overloaded. Converts an object into another type, irrespective of whether the conversion can be done at compile time or not. This can be used to convert generic types to numeric types during runtime. (Defined by ExtensionMethods.)

Top

Remarks

This class implements a linear activation function bounded in the interval (a,b), as given by the piecewise formula:

Copy

f(x) = alpha*x, if a > x*alpha > b
f(x) = a,       if a > x*alpha;
f(x) = b,       if     x*alpha > b;

In which, by default, a = -1 and b = +1.

This function is continuous only in the interval (a/alpha, b/alpha). This is similar to the threshold function but with a linear growth component. If alpha is set to a very high value (such as infinity), the function behaves as a threshold function.

The output range of the function can be set to an arbitrary value. The default output range is [-1, +1].

Reference

Accord.Neuro Namespace