<img src="https://raw.githubusercontent.com/liquidcarrot/carrot/master/images/carrot-logo_readme.png" alt="Carrot Logo" width="600px"/> <a href="https://travis-ci.org/liquidcarrot/carrot"> <img src="https://travis-ci.org/liquidcarrot/carrot.svg?branch=master" alt="Build Status via Travis CI"> </a> <a href="https://www.codacy.com/app/christianechevarria/carrot?utm_source=github.com&utm_medium=referral&utm_content=liquidcarrot/carrot&utm_campaign=Badge_Grade"> <img src="https://api.codacy.com/project/badge/Grade/3ee723b170f14b4990c8a0a6fc1feb27" alt="Codacy Badge"> </a> <a href="https://coveralls.io/github/liquidcarrot/carrot?branch=master"> <img src="https://coveralls.io/repos/github/liquidcarrot/carrot/badge.svg?branch=master" alt="Coverage Status"> </a> <a href="https://discord.gg/P4FJG8rEYC"> <img src="https://img.shields.io/discord/800482235852914698" alt="Join the chat on Discord at https://discord.gg/P4FJG8rEYC"> </a> <a href="/LICENSE"> <img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="Carrot's License"> </a> <a href="https://github.com/liquidcarrot/carrot/issues"> <img src="https://img.shields.io/badge/Made%20with%20%E2%99%A5%20by-Liquid%20Carrot-ff1414.svg" alt="Made with love"> </a> <h4>ℹ️ The new TypeScript version is coming! If you would like to try the expiremental version please clone the repository and checkout the typescript branch of the project. Docs for this new version can temporarily be found <a href="https://raimannma.github.io/carrot/index.html">here</a></h4> Carrot is an architecture-free neural network library built around neuroevolution Why / when should I use this?

Whenever you have a problem that you:

Don't know how-to solve
Don't want to design a custom network for
Want to discover the ideal neural-network structure for

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)
Preconfigured GRU, LSTM, NARX Networks
Mutable Neurons, Layers, Groups, and Networks
SVG Network Visualizations using D3.js

Demos

flappy bird neuro-evolution demo 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:

perceptron .

How to build it with Carrot:

let { architect } = require('@liquid-carrot/carrot');

// The example Perceptron you see above with 4 inputs, 5 hidden, and 1 output neuron
let simplePerceptron = new architect.Perceptron(4, 5, 1);

Building networks is easy with 6 built-in networks

let { architect } = require('@liquid-carrot/carrot');

let LSTM = new architect.LSTM(4, 5, 1);

// Add as many hidden layers as needed
let Perceptron = new architect.Perceptron(4, 5, 20, 5, 10, 1);

Building custom network architectures

let architect = require('@liquid-carrot/carrot').architect
let Layer = require('@liquid-carrot/carrot').Layer

let input = new Layer.Dense(1);
let hidden1 = new Layer.LSTM(5);
let hidden2 = new Layer.GRU(1);
let output = new Layer.Dense(1);

// connect however you want
input.connect(hidden1);
hidden1.connect(hidden2);
hidden2.connect(output);

let network = architect.Construct([input, hidden1, hidden2, output]);

Networks also shape themselves with neuro-evolution

let { Network, methods } = require('@liquid-carrot/carrot');

// this network learns the XOR gate (through neuro-evolution)
async function execute () {
  // no hidden layers...
   var network = new Network(2,1);

   // XOR dataset
   var trainingSet = [
       { input: [0,0], output: [0] },
       { input: [0,1], output: [1] },
       { input: [1,0], output: [1] },
       { input: [1,1], output: [0] }
   ];

   await network.evolve(trainingSet, {
       mutation: methods.mutation.FFW,
       equal: true,
       error: 0.05,
       elitism: 5,
       mutation_rate: 0.5
   });

   // and it works!
   network.activate([0,0]); // 0.2413
   network.activate([0,1]); // 1.0000
   network.activate([1,0]); // 0.7663
   network.activate([1,1]); // 0.008
}

execute();

Build vanilla neural networks

let Network = require('@liquid-carrot/carrot').Network

let network = new Network([2, 2, 1]) // Builds a neural network with 5 neurons: 2 + 2 + 1

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):

<table> <tr> <td align="center"><a href="https://liquidcarrot.io/"><img src="https://avatars3.githubusercontent.com/u/21148993?v=4" width="100px;" alt=""/> Luis Carbonell</a> <a href="https://github.com/liquidcarrot/carrot/commits?author=luiscarbonell" title="Code">💻</a> <a href="#ideas-luiscarbonell" title="Ideas, Planning, & Feedback">🤔</a> <a href="https://github.com/liquidcarrot/carrot/pulls?q=is%3Apr+reviewed-by%3Aluiscarbonell" title="Reviewed Pull Requests">👀</a> <a href="https://github.com/liquidcarrot/carrot/commits?author=luiscarbonell" title="Documentation">📖</a></td> <td align="center"><a href="http://liquidcarrot.io"><img src="https://avatars2.githubusercontent.com/u/23618650?v=4" width="100px;" alt=""/> Christian Echevarria</a> <a href="https://github.com/liquidcarrot/carrot/commits?author=christianechevarria" title="Code">💻</a> <a href="https://github.com/liquidcarrot/carrot/commits?author=christianechevarria" title="Documentation">📖</a> <a href="#infra-christianechevarria" title="Infrastructure (Hosting, Build-Tools, etc)">🚇</a></td> <td align="center"><a href="https://github.com/dan-ryan"><img src="https://avatars1.githubusercontent.com/u/775672?v=4" width="100px;" alt=""/> Daniel Ryan</a> <a href="https://github.com/liquidcarrot/carrot/issues?q=author%3Adan-ryan" title="Bug reports">🐛</a> <a href="https://github.com/liquidcarrot/carrot/pulls?q=is%3Apr+reviewed-by%3Adan-ryan" title="Reviewed Pull Requests">👀</a></td> <td align="center"><a href="https://github.com/IviieMtz"><img src="https://avatars0.githubusercontent.com/u/50965172?v=4" width="100px;" alt=""/> IviieMtz</a> <a href="https://github.com/liquidcarrot/carrot/commits?author=IviieMtz" title="Tests">⚠️</a></td> <td align="center"><a href="https://github.com/nicszerman"><img src="https://avatars3.githubusercontent.com/u/14032356?v=4" width="100px;" alt=""/> Nicholas Szerman</a> <a href="https://github.com/liquidcarrot/carrot/commits?author=nicszerman" title="Code">💻</a></td> <td align="center"><a href="http://www.threeceemedia.com"><img src="https://avatars3.githubusercontent.com/u/1046501?v=4" width="100px;" alt=""/> tracy collins</a> <a href="https://github.com/liquidcarrot/carrot/issues?q=author%3Atracycollins" title="Bug reports">🐛</a></td> <td align="center"><a href="https://github.com/raimannma"><img src="https://avatars3.githubusercontent.com/u/26171511?v=4" width="100px;" alt=""/> Manuel Raimann</a> <a href="https://github.com/liquidcarrot/carrot/issues?q=author%3Araimannma" title="Bug reports">🐛</a> <a href="https://github.com/liquidcarrot/carrot/commits?author=raimannma" title="Code">💻</a> <a href="#ideas-raimannma" title="Ideas, Planning, & Feedback">🤔</a></td> </tr> </table>

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

Carrot

Install / Use

README