Enum cosyne::Activation

pub enum Activation {
    Linear,
    Threshold,
    Sign,
    Sigmoid,
    Tanh,
    SoftSign,
    BentIdentity,
    Relu,
}

Represents which transfer function to use for evaluating neural networks.

Variants

Linear

Maps input to output directly, as if there is no transfer function.

Threshold

Outputs 1 if input is greater than 0, 0 otherwise.

Sign

Outputs 1 if input is greater than 0, 0 if input is equal to 0, -1 otherwise. Useful for simple problems and boolean logic, as it only allows three possible output values.

Sigmoid

A non-linear function. This function is the most general, so it should be defaulted to.

Tanh

Tanh activation function with output range [-1.0, 1.0]

SoftSign

SoftSign activation function

BentIdentity

BentIdentity activation function

Relu

Rectified linear unit activation function

Implementations

impl Activation

pub fn get_func(&self) -> fn(_: f64) -> f64

Return the corresponding function to the Activation

pub fn from_i32(n: i32) -> Activation

parse the Activation from an int 32 value

Trait Implementations

impl Clone for Activation

fn clone(&self) -> Activation

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Copy for Activation

impl Debug for Activation

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

Formats the value using the given formatter.

impl Eq for Activation

impl PartialEq<Activation> for Activation

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

This method tests for self and other values to be equal, and is used by ==.

#[must_use]pub fn ne(&self, other: &Rhs) -> bool

This method tests for !=.

impl StructuralEq for Activation

impl StructuralPartialEq for Activation