CODEWITHSUNDEEP
javascriptmachine-learningneural-network
user2346766
user2346766

Reputation:

brain.js: XOR example does not work

I'm trying to understand brain.js.

This is my code; it does not work. (Explaination of what I expect it to do below)

<script src="https://cdn.rawgit.com/harthur/brain/gh-pages/brain-0.6.3.min.js">

<script>
var net = new brain.NeuralNetwork();

net.train([{input: [0, 0], output: [0]},
           {input: [0, 1], output: [1]},
           {input: [1, 0], output: [1]},
           {input: [1, 1], output: [0]}]);

var output = net.run([1, 0]);
document.write(output[1]);
</script>

This code imports the brain.min.js code and then teaches a neural network how to do the XOR operation

I expect it to return 0.978 (or somewhere around that), but I'm staring at a blank HTML page. I hope someone who's feeling helpful points me in the right direction. Thanks!

Upvotes: 0

Views: 692

Answers (2)

Anton Vlasenko
Anton Vlasenko

Reputation: 51

This code works in 2019:

<html>
<head>
    <script src="https://unpkg.com/brain.js"></script>
</head>
<body>
<script>
    const net = new brain.NeuralNetwork({hiddenLayers: [3]});

    net.train([{input: [0, 0], output: [0]},
        {input: [0, 1], output: [1]},
        {input: [1, 0], output: [1]},
        {input: [1, 1], output: [0]}]);

    const output = net.run([0, 1]);
    document.write(output[0])
</script>
</body>
</html>

Upvotes: 0

jhinzmann
jhinzmann

Reputation: 988

Arrays in JavaScript are zero based.

Therefore you have to use document.write(output[0]);.

Maybe it would be helpfull to use a console.log or even better a debugger; statement. This way you can inspect your variables through the JS Console.

More info on debugging can be found here.

Upvotes: 1

Related Questions