Trait Layer

pub trait Layer<S, D>
where
    D: Dimension,
    S: RawData<Elem = Self::Elem>,
{
    type Elem;
    type Rho: Activator<Self::Elem>;

    // Required methods
    fn rho(&self) -> &Self::Rho;
    fn params(&self) -> &ParamsBase<S, D>;
    fn params_mut(&mut self) -> &mut ParamsBase<S, D>;
}

A generic trait defining the composition of a layer within a neural network.

Required Associated Types

type Elem

the type of element used within the layer; typically a floating-point variant like f32 or f64.

type Rho: Activator<Self::Elem>

The type of activator used by the layer; the type must implement ActivatorGradient

Required Methods

fn rho(&self) -> &Self::Rho

fn params(&self) -> &ParamsBase<S, D>

returns an immutable reference to the parameters of the layer

fn params_mut(&mut self) -> &mut ParamsBase<S, D>

returns a mutable reference to the parameters of the layer

Implementors

impl<A, F, S, D> Layer<S, D> for LayerBase<F, S, D>

where F: Activator<A, Output = A>, D: Dimension, S: RawData<Elem = A>,

type Elem = A

type Rho = F