Enum ActivationFn 

pub enum ActivationFn {
    Tanh,
    Relu,
    Sigmoid,
    Silu,
    Gelu,
    Linear,
}

Activation functions for neural network layers.

Variants

Tanh

Hyperbolic tangent.

Relu

Rectified linear unit.

Sigmoid

Logistic sigmoid.

Silu

Sigmoid-weighted linear unit.

Gelu

Gaussian error linear unit (approximation).

Linear

Identity / no activation.

Implementations

impl ActivationFn

pub fn apply(&self, x: f32) -> f32

Evaluate the activation function at x.

pub fn derivative(&self, x: f32) -> f32

Evaluate the derivative of the activation function at x.

Trait Implementations

impl Clone for ActivationFn

fn clone(&self) -> ActivationFn

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ActivationFn

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl PartialEq for ActivationFn

fn eq(&self, other: &ActivationFn) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for ActivationFn