diwa_activations.h File Reference

Defines activation functions for use in the Diwa neural network. More...

#include <diwa_conv.h>
#include <math.h>

Go to the source code of this file.

Classes
class	DiwaActivationFunc
	Class containing static methods for common activation functions. More...

Macros
#define	DIWA_ACTFUNC_LOWER_BOUND   -30.0f
#define	DIWA_ACTFUNC_UPPER_BOUND   30.0f

Typedefs
typedef double(*	diwa_activation) (double)
	Typedef for activation function pointer.

Detailed Description

Defines activation functions for use in the Diwa neural network.

Author

Nathanne Isip

This header file defines the DiwaActivationFunc class, which provides a set of common activation functions used in neural networks. Activation functions play a crucial role in determining the output of a neuron based on its input. They introduce non-linearity to the network, allowing it to learn complex patterns and relationships in the data.

The DiwaActivationFunc class contains static methods for popular activation functions, including sigmoid and gaussian functions. These activation functions are used to introduce non-linearity and regulate the output values of neurons in the neural network. They transform the input values into output values suitable for the task at hand, such as classification or regression.

Note

Activation functions are an essential component of neural networks and significantly influence the network's learning dynamics and performance. The choice of activation function depends on the nature of the problem being solved and the characteristics of the dataset.

Macro Definition Documentation

DIWA_ACTFUNC_LOWER_BOUND

#define DIWA_ACTFUNC_LOWER_BOUND   -30.0f

Lower bound for input values to prevent overflow.

DIWA_ACTFUNC_UPPER_BOUND

#define DIWA_ACTFUNC_UPPER_BOUND   30.0f

Upper bound for input values to prevent overflow.

Typedef Documentation

diwa_activation

typedef double(* diwa_activation) (double)

Typedef for activation function pointer.

This typedef defines the signature for activation functions used in the Diwa neural network. Activation functions take a single input value and return a transformed output value.