Softplus

Full name Microsoft.VisualBasic.MachineLearning.ComponentModel.Activations.Softplus Assembly Microsoft.VisualBasic.MachineLearning Members 4

The softplus activation function: f(x) = ln(1 + e ^ x).

00 Remarks

Softplus is a smooth approximation of the ReLU function, and its derivative is the standard logistic sigmoid function.

01 Syntax

Microsoft.VisualBasic.MachineLearning.ComponentModel.Activations.Softplus

02 Methods

Name	Overloads	Summary
Function	1	Calculates the softplus function value: ln(1 + e ^ x).
ToString	1	Display this activation function as a text expression.
Derivative	1	Calculates the derivative of the softplus function, which equals to the logistic sigmoid function: f'(x) = 1 / (1 + e ^ -x).

03 Properties

Name	Overloads	Summary
Store	1	Gets the XML serializable data model of this softplus function.

04 Members

method Function #

Function(Double)

Calculates the softplus function value: ln(1 + e ^ x).

Parameters

Name	Type	Description
`x`	`Double`	The function input value.

Returns

The function output value.

method ToString #

ToString

Display this activation function as a text expression.

Returns

The text expression of this softplus function.

method Derivative #

Derivative(Double)

Calculates the derivative of the softplus function, which equals to the logistic sigmoid function: f'(x) = 1 / (1 + e ^ -x).

Parameters

Name	Type	Description
`x`	`Double`	The function input value.

Returns

The derivative value.

property Store #

Store

Gets the XML serializable data model of this softplus function.

Returns

A ActiveFunction data model which its function name is Softplus and no argument is required.