Edge Rewrite
// HTMLRewriter · presentation

This page was redesigned at the edge.

Cloudflare fetched the original article and streamed it through HTMLRewriter to apply an entirely new visual system without rebuilding the source page.

Jump to content

Brain.js

From Wikipedia, the free encyclopedia
Brain.js
DeveloperOpen-source contributors
ReleaseMay 10, 2010; 16 years ago (2010-05-10)
Written inJavaScript, TypeScript
PlatformNode.js, Web browser
TypeNeural Networking
LicenseMIT License
Websitebrain.js.org
RepositoryBrain.js Repository

Brain.js is a JavaScript library used for neural networking, which is released as free and open-source software under the MIT License.[1] It can be used in both the browser and Node.js backends.[2][3]

Brain.js is most commonly used as a simple introduction to neural networking, as it hides complex mathematics and has a familiar modern JavaScript syntax.[4][5] It is maintained by members of the Brain.js organization and open-source contributors.

Examples

[edit]

Creating a feedforward neural network with backpropagation:

const 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] },
]);

console.log(net.run([1, 0]));

Creating a recurrent neural network:

const net = new brain.recurrent.RNN();

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

let output = net.run([0, 0]); // [0]
output = net.run([0, 1]); // [1]
output = net.run([1, 0]); // [1]
output = net.run([1, 1]); // [0]

Train the neural network on RGB color contrast:

const net = new brain.NeuralNetwork();

net.train([{
    input: {
      r: 0.03,
      g: 0.7,
      b: 0.5
    },
    output: {
      black: 1
    }
  },
  {
    input: {
      r: 0.16,
      g: 0.09,
      b: 0.2
    },
    output: {
      white: 1
    }
  },
  {
    input: {
      r: 0.5,
      g: 0.5,
      b: 1.0
    },
    output: {
      white: 1
    }
  }
]);

const output = net.run({
  r: 1,
  g: 0.4,
  b: 0
}); // { white: 0.99, black: 0.002 }

console.log(output)
[edit]

References

[edit]
  1. Eschweiler, Sebastian (2020-09-09). "Beginner's Guide To Neural Networks In JavaScript With Brain.js". CodingTheSmartWay.com Blog. Retrieved 2022-03-19.
  2. Dijkhuizen, Bryan (2021-11-02). "Machine Learning in JavaScript Using Brain.js for Simple Applications". Medium. Retrieved 2022-03-19.
  3. "Neural Networks In JavaScript - Brain.js Tutorial". Scrimba. Retrieved 2022-03-13.
  4. "Build and train a neural network with nothing but JavaScript using Brain.js". IBM Developer. Retrieved 2022-03-19.
  5. "Brain.js". www.w3schools.com. Retrieved 2022-03-19.