Diwa
Lightweight implementation of Artificial Neural Network for resource-constrained environments
Loading...
Searching...
No Matches
DiwaActivationFunc Class Referencefinal

Class containing static methods for common activation functions. More...

#include <diwa_activations.h>

Static Public Member Functions

static double sigmoid (double x)
 Sigmoid activation function.
 
static double gaussian (double x)
 Gaussian activation function.
 

Detailed Description

Class containing static methods for common activation functions.

The DiwaActivationFunc class provides a set of static methods for common activation functions used in neural networks. These activation functions transform the input value to produce the output value of a neuron. Supported activation functions include sigmoid and gaussian functions.

Member Function Documentation

◆ gaussian()

static double DiwaActivationFunc::gaussian ( double  x)
inlinestatic

Gaussian activation function.

The gaussian activation function takes an input value and returns the corresponding output value after applying the gaussian transformation. It produces a bell-shaped curve, ensuring that the output value decreases smoothly as the input value moves away from the center.

Parameters
xThe input value to be transformed.
Returns
The transformed output value after applying the gaussian function.

◆ sigmoid()

static double DiwaActivationFunc::sigmoid ( double  x)
inlinestatic

Sigmoid activation function.

The sigmoid activation function takes an input value and returns the corresponding output value after applying the sigmoid transformation. It ensures that the output value is bounded between 0 and 1, suitable for binary classification tasks and preventing overflow.

Parameters
xThe input value to be transformed.
Returns
The transformed output value after applying the sigmoid function.

The documentation for this class was generated from the following file: