Struct NeuralNetwork

pub struct NeuralNetwork<const I: usize, const H: usize> {
    pub hidden_layer: [Neuron<I>; H],
    pub output_layer: Neuron<H>,
}

A simple neural network with I inputs and one hidden layer of H neurons.

The network has a single output, use multiple networks for multiple outputs.

Fields

hidden_layer: [Neuron<I>; H]

output_layer: Neuron<H>

Implementations

impl<const I: usize, const H: usize> NeuralNetwork<I, H>

pub fn output(&self, x: &[f32; I]) -> f32

Computes the network’s output for x.

pub fn train<'a>( &mut self, data: impl Iterator<Item = &'a ([f32; I], f32)>, epsilon: f32, )

Trains the network from data using back-propagation with epsilon learning rate (per data entry).

Trait Implementations

impl<const I: usize, const H: usize> Clone for NeuralNetwork<I, H>

fn clone(&self) -> NeuralNetwork<I, H>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<const I: usize, const H: usize> Debug for NeuralNetwork<I, H>

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

Formats the value using the given formatter.