Struct NeuralNet

Source

pub struct NeuralNet<A: Activation> { /* private fields */ }

Expand description

A fully-connected neural network.

Implementations§

Source §

impl<A: Activation + Serialize + DeserializeOwned> NeuralNet<A>

Source

pub fn new(node_counts: &[usize]) -> Self

Creates a new NeuralNet with the given node configuration.

Note that you must supply a type annotation so that it knows which Activation to use.

§Examples

use scholar::{NeuralNet, Sigmoid};

// Creates a neural network with two input nodes, a single hidden layer with two nodes,
// and one output node
let brain: NeuralNet<Sigmoid> = NeuralNet::new(&[2, 2, 1]);

§Panics

This function panics if the number of layers (i.e. the length of the given node_counts slice) is less than 2.

Source

pub fn from_file(path: impl AsRef<Path>) -> Result<Self, LoadErr>

Creates a new NeuralNet from a valid file (those created using NeuralNet::save()).

§Examples

use scholar::{NeuralNet, Sigmoid};

let brain: NeuralNet<Sigmoid> = NeuralNet::from_file("brain.network")?;

Source

pub fn train( &mut self, training_dataset: Dataset, iterations: u64, learning_rate: f64, )

Trains the network on the given Dataset for the given number of iterations.

§Examples

use scholar::{Dataset, NeuralNet, Sigmoid};

let dataset = Dataset::from_csv("iris.csv", false, 4)?;

let mut brain: NeuralNet<Sigmoid> = NeuralNet::new(&[4, 10, 10, 1]);

// Trains the network by iterating over the entire dataset 10,000 times. The last parameter
// (the 'learning rate') dictates how quickly the network 'adapts to the dataset'
brain.train(dataset, 10_000, 0.01);

Source

pub fn test(&mut self, testing_dataset: Dataset) -> f64

Calculates the average cost of the network.

§Examples

use scholar::{Dataset, NeuralNet, Sigmoid};

let dataset = Dataset::from_csv("iris.csv", false, 4)?;
let (training_data, testing_data) = dataset.split(0.75);

let mut brain: NeuralNet<Sigmoid> = NeuralNet::new(&[4, 10, 10, 1]);
brain.train(training_data, 10_000, 0.01);

let avg_cost = brain.test(testing_data);
println!("Accuracy: {:.2}%", (1.0 - avg_cost) * 100.0);

Source

pub fn save(&self, path: impl AsRef<Path>) -> Result<(), SaveErr>

Saves the network in a binary format to the specified path.

§Examples

use scholar::{NeuralNet, Sigmoid};

let brain: NeuralNet<Sigmoid> = NeuralNet::new(&[2, 2, 1]);

// Note that the file doesn't have to use the '.network' extension; you can actually
// choose anything you wish!
brain.save("brain.network")?;

Source

pub fn guess(&mut self, inputs: &[f64]) -> Vec<f64>

Performs the feedforward algorithm on the given input slice, returning the value of the output layer as a vector.

§Examples

use scholar::{NeuralNet, Sigmoid};

let mut brain: NeuralNet<Sigmoid> = NeuralNet::new(&[3, 10, 2]);
let result = brain.guess(&[1.0, 0.0, -0.5]);

assert_eq!(result.len(), 2);