C# 클래스 AForge.Neuro.SigmoidFunction

Sigmoid activation function.

The class represents sigmoid activation function with the next expression: 1 f(x) = ------------------ 1 + exp(-alpha * x) alpha * exp(-alpha * x ) f'(x) = ---------------------------- = alpha * f(x) * (1 - f(x)) (1 + exp(-alpha * x))^2

Output range of the function: [0, 1].

Functions graph:

상속: IActivationFunction
파일 보기 프로젝트 열기: holisticware-admin/MonoVersal.AForgeNET 1 사용 예제들

공개 메소드들

메소드 설명
Clone ( ) : object

Creates a new object that is a copy of the current instance.

Derivative ( double x ) : double

Calculates function derivative.

The method calculates function derivative at point x.

Derivative2 ( double y ) : double

Calculates function derivative.

The method calculates the same derivative value as the Derivative method, but it takes not the input x value itself, but the function value, which was calculated previously with the help of Function method.

Some applications require as function value, as derivative value, so they can save the amount of calculations using this method to calculate derivative.

Function ( double x ) : double

Calculates function value.

The method calculates function value at point x.

SigmoidFunction ( ) : System

Initializes a new instance of the SigmoidFunction class.

SigmoidFunction ( double alpha ) : System

Initializes a new instance of the SigmoidFunction class.

메소드 상세

Clone() 공개 메소드

Creates a new object that is a copy of the current instance.
public Clone ( ) : object
리턴 object

Derivative() 공개 메소드

Calculates function derivative.
The method calculates function derivative at point x.
public Derivative ( double x ) : double
x double Function input value.
리턴 double

Derivative2() 공개 메소드

Calculates function derivative.

The method calculates the same derivative value as the Derivative method, but it takes not the input x value itself, but the function value, which was calculated previously with the help of Function method.

Some applications require as function value, as derivative value, so they can save the amount of calculations using this method to calculate derivative.

public Derivative2 ( double y ) : double
y double Function output value - the value, which was obtained /// with the help of method.
리턴 double

Function() 공개 메소드

Calculates function value.
The method calculates function value at point x.
public Function ( double x ) : double
x double Function input value.
리턴 double

SigmoidFunction() 공개 메소드

Initializes a new instance of the SigmoidFunction class.
public SigmoidFunction ( ) : System
리턴 System

SigmoidFunction() 공개 메소드

Initializes a new instance of the SigmoidFunction class.
public SigmoidFunction ( double alpha ) : System
alpha double Sigmoid's alpha value.
리턴 System