raimannma_testing v0.6.2

You can use Carrot's ability to design networks of arbitrary complexity by itself to solve whatever problem you have. If you want to see Carrot designing a neural-network to play flappy-bird check here

For Documentation, visit here

Key Features

• Simple docs & interactive examples
• Neuro-evolution & population based training
• Multi-threading & GPU (coming soon)
• Complete customizable Networks with various types of layers
• Mutable Neurons, Connections, Layers, and Networks

Demos

Flappy bird neuro-evolution

Install

$ npm i @liquid-carrot/carrot

Carrot files are hosted by JSDelivr

For prototyping or learning, use the latest version here:

<script src="https://cdn.jsdelivr.net/npm/@liquid-carrot/carrot/dist/carrot.umd2.min.js"></script>

For production, link to a specific version number to avoid unexpected breakage from newer versions:

<script src="https://cdn.jsdelivr.net/npm/@liquid-carrot/carrot@0.3.17/dist/carrot.umd2.min.js"></script>

Getting Started

💡 Want to be super knowledgeable about neuro-evolution in a few minutes?

Check out this article by the creator of NEAT, Kenneth Stanley

💡 Curious about how neural-networks can understand speech and video?

Check out this video on Recurrent Neural Networks, from @LearnedVector, on YouTube

This is a simple perceptron:

.

How to build it with Carrot:

const architect = new Architect();

architect.addLayer(new InputLayer(4));
architect.addLayer(new DenseLayer(5, { activationType: RELUActivation }));
architect.addLayer(new OutputLayer(1));

const network = architect.buildModel();

Building networks is easy with 17 built-in layers You can combine them as you need.

const architect = new Architect();

architect.addLayer(new InputLayer(10));
architect.addLayer(new DenseLayer(10, { activationType: RELUActivation }));
architect.addLayer(new MaxPooling1DLayer(5, { activation: IdentityActivation }));
architect.addLayer(new OutputLayer(2, { activation: RELUActivation }));

const network = architect.buildModel();

Networks also shape themselves with neuro-evolution

const XOR = [
  { input: [0, 0], output: [0] },
  { input: [0, 1], output: [1] },
  { input: [1, 0], output: [1] },
  { input: [1, 1], output: [0] },
];

// this network learns the XOR gate (through neuro-evolution)
async function execute(): Promise<void> {
  this.timeout(20000);

  const network: Network = new Network(2, 1);

  const initial: number = network.test(XOR);
  await network.evolve({ iterations: 50, dataset: XOR });
  const final: number = network.test(XOR);

  expect(final).to.be.at.most(initial);
}

execute();

Or implement custom algorithms with neuron-level control

let Node = require("@liquid-carrot/carrot").Node;

let A = new Node(); // neuron
let B = new Node(); // neuron

A.connect(B);
A.activate(0.5);
console.log(B.activate());

Try with

Data Sets

• MNIST

Contributors ✨

This project exists thanks to all the people who contribute. We can't do it without you! 🙇

Thanks goes to these wonderful people (emoji key):

This project follows the all-contributors specification. Contributions of any kind welcome!

💬 Contributing

Your contributions are always welcome! Please have a look at the contribution guidelines first. 🎉

To build a community welcome to all, Carrot follows the Contributor Covenant Code of Conduct.

And finally, a big thank you to all of you for supporting! 🤗

Patrons

Acknowledgements

A special thanks to:

@wagenaartje for Neataptic which was the starting point for this project

@cazala for Synaptic which pioneered architecture free neural networks in javascript and was the starting point for Neataptic

@robertleeplummerjr for GPU.js which makes using GPU in JS easy and Brain.js which has inspired Carrot's development