Enum ActivationFn64 

pub enum ActivationFn64 {
    Relu,
    Sigmoid,
    Tanh,
    Linear,
}

Activation function for f64-precision neural network layers.

Variants

Relu

Rectified linear unit: max(0, x).

Sigmoid

Logistic sigmoid: 1 / (1 + exp(-x)).

Tanh

Hyperbolic tangent.

Linear

Identity (no activation).

Implementations

impl ActivationFn64

pub fn apply(&self, x: f64) -> f64

Evaluate the activation at a single value.

pub fn apply_batch(&self, v: &mut Vec<f64>)

Apply the activation in-place to every element of a vector.

Trait Implementations

impl Clone for ActivationFn64

fn clone(&self) -> ActivationFn64

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ActivationFn64

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

Formats the value using the given formatter.

impl PartialEq for ActivationFn64

fn eq(&self, other: &ActivationFn64) -> 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 ActivationFn64