Struct NeuralNetwork

pub struct NeuralNetwork { /* private fields */ }

A simple feedforward neural network with one hidden layer.

Implementations

impl NeuralNetwork

pub fn new(input_size: usize, hidden_size: usize, output_size: usize) -> Self

Creates a new neural network with the given sizes for input, hidden, and output layers. The weights and biases are initialized randomly.

pub fn set_learning_rate(&mut self, learning_rate: f64)

Sets the learning rate for the neural network.

pub fn set_activation_function( &mut self, activation_function: fn(&Matrix) -> Matrix, activation_function_derivative: fn(&Matrix) -> Matrix, )

Sets the activation function for the neural network.

pub fn set_linear_activation(&mut self)

pub fn set_sigmoid_activation(&mut self)

pub fn set_tanh_activation(&mut self)

pub fn predict(&self, input: Vec<f64>) -> Vec<f64>

Predicts the output for the given input using the neural network.

pub fn train(&mut self, input: Vec<f64>, target: Vec<f64>)

Trains the neural network using the given input and target output. The input and target should be vectors of the same length as the input and output sizes of the network. The training process involves forward propagation and backpropagation to adjust the weights and biases.

Trait Implementations

impl Clone for NeuralNetwork

fn clone(&self) -> NeuralNetwork

Returns a copy 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.