Struct NeuralNetwork 

pub struct NeuralNetwork {
    pub layers: Vec<NeuralLayer>,
}

A sequential feed-forward neural network using f64 precision.

Fields

layers: Vec<NeuralLayer>

Ordered list of layers.

Implementations

impl NeuralNetwork

pub fn new(layer_sizes: &[usize], activation: ActivationFn64) -> Self

Build a network with Xavier-initialised weights from a list of layer sizes.

All hidden layers use activation; the final layer uses ActivationFn64::Linear.

pub fn forward(&self, input: &[f64]) -> Vec<f64>

Run a forward pass through all layers.

pub fn input_dim(&self) -> usize

Expected input dimension (size of the first layer’s input).

pub fn output_dim(&self) -> usize

Expected output dimension (size of the last layer’s output).

Trait Implementations

impl Clone for NeuralNetwork

fn clone(&self) -> NeuralNetwork

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for NeuralNetwork

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

Formats the value using the given formatter.