Struct ReLU 

pub struct ReLU;

Rectified Linear Unit (ReLU) activation function.

Outputs the input directly if it is positive; otherwise, it outputs zero.

Mathematical Definition

For an input x, the ReLU function is defined as:

 \text{ReLU}(x) = \max(x, 0)

or

 \text{ReLU}(x) = \left\{
\begin{array}{ll}
x & \text{if } x \geq 0 \\
0 & \text{if } x < 0
\end{array}
\right.

See Also

• Wikipedia: Rectifier (neural networks)

Implementations

impl ReLU

pub fn new() -> Self

Trait Implementations

impl<T: Float> Function<T> for ReLU

fn derivative(&self, matrix: Matrix<T>) -> Matrix<T>

Derivative of Relu

  ReLU'(x) = \left\{
 \begin{array}{ll}
 1 & \text{if } x \geq 0 \\
 0 & \text{if } x < 0
 \end{array}
 \right.

fn name(&self) -> String

fn call(&self, matrix: Matrix<T>) -> Matrix<T>

Applies the function to the input matrix.

fn is_linear(&self) -> bool

fn get_data(&self) -> Option<Matrix<T>>

fn set_data(&mut self, _data: Matrix<T>)

fn get_weights(&self) -> Option<Matrix<T>>

fn get_bias(&self) -> Option<Matrix<T>>

fn is_bias(&self) -> bool