ailayer_relu Struct Reference

General ReLU layer struct. More...

#include <ailayer_relu.h>

Data Fields
ailayer_t	base
	Inherited field members from general ailayer struct.
Math functions
Required data type specific math functions
void(*	relu )(const aitensor_t *x, aitensor_t *result)
	Required math function: ReLU. More...
void(*	d_relu )(const aitensor_t *x, aitensor_t *result)
	Required math function: Derivative of ReLU. More...
void(*	multiply )(const aitensor_t *a, const aitensor_t *b, aitensor_t *result)
	Required math function: Element wise tensor multiplication. More...

Detailed Description

General ReLU layer struct.

Field Documentation

d_relu

void(* d_relu) (const aitensor_t *x, aitensor_t *result)

Required math function: Derivative of ReLU.

Requires a math function that calculates the element wise ReLU derivative of a tensor:

\[ result_{i} = \begin{cases} 0 & \text{if } x_i < 0\\ 1 & \text{if } x_i \geq 0 \end{cases} \]

Parameters

x	N-dimensional tensor (input)
result	N-dimensional tensor (output)

multiply

void(* multiply) (const aitensor_t *a, const aitensor_t *b, aitensor_t *result)

Required math function: Element wise tensor multiplication.

Requires a math function that multiplies two tensors element wise:

\[ result = a \circ b \]

relu

void(* relu) (const aitensor_t *x, aitensor_t *result)

Required math function: ReLU.

Requires a math function that calculates the element wise ReLU of a tensor:

\[ result_{i} = max(0, x_{i}) \]

Parameters

x	N-dimensional tensor (input)
result	N-dimensional tensor (output)

---

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

• ailayer_relu.h