jarnet

    0.11.22 • Public • Published

    Backpropagation Algorithm

    Example of usage in architecture.js file
    Configuration:
    {
        epochs: 90,             
        stopOnError: 0.01,      //  break iteration when achieved error
        neuronNrHidden: 2,      //  quantity of neurons in hidden layer
        learningRate: 0.2,      
        datasets: [],           //  array with data arrays with [input, input, output]
        logging: true           //  log info to console
    }
    
    Usage:
    const Net = require('./');
    
    let net = new Net();
    net.setup({
        epochs: 90,
        neuronNrHidden: 2,
        learningRate: 0.2,
        datasets: [ [1, 1, 0], [0, 0, 1], [1, 0, 1], [0, 1, 1] ],
        logging: true
    
    });
    net.train();
    net.test();                 //  compare trained network with provided data for training
    
    net.predict([1, 1]);        //  => returns 0
    
    //  saving model
    net.save('trained_network.json');
    net.saveSync('trained_network.json');
    
    //  loading model
    net.load('trained_network.json');
    net.loadSync('trained_network.json');
    
    
    ES6.
    No Babel.

    Install

    npm i jarnet

    DownloadsWeekly Downloads

    5

    Version

    0.11.22

    License

    ISC

    Last publish

    Collaborators

    • kerajon