Enum Activation 

pub enum Activation {
    ReLU,
    Tanh,
    Sigmoid,
    Erf,
    Linear,
    GELU,
    Swish,
}

Activation functions for neural network kernels

Variants

ReLU

ReLU activation: max(0, x)

Tanh

Tanh activation

Sigmoid

Sigmoid activation: 1 / (1 + exp(-x))

Erf

Error function (erf)

Linear

Linear activation (identity)

GELU

GELU activation

Swish

Swish activation: x * sigmoid(x)

Implementations

impl Activation

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

Apply activation function element-wise

pub fn kernel_value(&self, rho: Float) -> Float

Compute the kernel for this activation at correlation rho This is used in NTK computation

Trait Implementations

impl Clone for Activation

fn clone(&self) -> Activation

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Activation

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Activation

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for Activation

fn eq(&self, other: &Activation) -> 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 Serialize for Activation

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Copy for Activation

impl StructuralPartialEq for Activation