https://github.com/liquidcarrot/carrot

🥕 Evolutionary Neural Networks in JavaScript
https://github.com/liquidcarrot/carrot

browser easy-to-use javascript lstm machine-learning neat neural-networks neuro-evolution nodejs recurrent-neural-networks

Last synced: 2 months ago
JSON representation

🥕 Evolutionary Neural Networks in JavaScript

Host: GitHub
URL: https://github.com/liquidcarrot/carrot
Owner: liquidcarrot
License: mit
Created: 2018-12-03T19:31:26.000Z (over 6 years ago)
Default Branch: master
Last Pushed: 2023-01-07T02:40:18.000Z (over 2 years ago)
Last Synced: 2025-04-09T17:19:59.367Z (2 months ago)
Topics: browser, easy-to-use, javascript, lstm, machine-learning, neat, neural-networks, neuro-evolution, nodejs, recurrent-neural-networks
Language: JavaScript
Homepage: https://liquidcarrot.io/carrot/
Size: 17 MB
Stars: 295
Watchers: 17
Forks: 33
Open Issues: 103
Metadata Files:
- Readme: README.md
- Contributing: CONTRIBUTING.md
- Funding: .github/FUNDING.yml
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md

Awesome Lists containing this project

README

        


 





    

        

    

    

        

    

    

        

    

    

        

    

    

        

    

    

        

    



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 here





  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](https://liquidcarrot.io/example.flappy-bird/)

 



For Documentation, visit [here](https://liquidcarrot.github.io/carrot)

## Key Features

- [Simple docs](https://liquidcarrot.github.io/carrot) & [interactive examples](https://liquidcarrot.io/example.flappy-bird/)

- **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](https://raw.githubusercontent.com/liquidcarrot/carrot/master/images/flappy-bird-demo.gif)




[Flappy bird neuro-evolution](https://liquidcarrot.io/example.flappy-bird/ "flappy bird playground")

## Install

```bash

$ npm i @liquid-carrot/carrot

```

Carrot files are hosted by JSDelivr

For prototyping or learning, use the latest version here:

```html

```

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

```html

```

## Getting Started

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

Check out [this article](https://www.oreilly.com/radar/neuroevolution-a-different-kind-of-deep-learning/ "Neuro-evolution based deep learning") 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](https://www.youtube.com/watch?v=LHXXI4-IEns), from [@LearnedVector](https://github.com/LearnedVector), on YouTube

This is a simple **perceptron**:

![perceptron](http://www.codeproject.com/KB/dotnet/predictor/network.jpg).

How to build it with Carrot:

```javascript

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

```javascript

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

```javascript

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

```javascript

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

```javascript

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

```javascript

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](https://www.npmjs.com/package/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](https://allcontributors.org/docs/en/emoji-key)):

  

    
_{Luis Carbonell}
💻 🤔 👀 📖

    
_{Christian Echevarria}
💻 📖 🚇

    
_{Daniel Ryan}
🐛 👀

    
_IviieMtz
⚠️

    
_{Nicholas Szerman}
💻

    
_{tracy collins}
🐛

    
_{Manuel Raimann}
🐛 💻 🤔

  

This project follows the [all-contributors](https://github.com/all-contributors/all-contributors) specification. Contributions of any kind welcome!

## 💬 Contributing

[![Carrot's GitHub Issues](https://img.shields.io/github/issues/liquidcarrot/carrot.svg)](https://github.com/liquidcarrot/carrot/issues)

Your contributions are always welcome! Please have a look at the [contribution guidelines](https://github.com/liquidcarrot/carrot/blob/master/CONTRIBUTING.md) first. 🎉

To build a community welcome to all, Carrot follows the [Contributor Covenant](https://github.com/liquidcarrot/carrot/blob/master/CODE_OF_CONDUCT.md) Code of Conduct.

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

Planned Features

* [ ] Performance Enhancements

    * [ ] GPU Acceleration

        * [ ] Tests

        * [ ] Benchmarks

    * [ ] Matrix Multiplications

        * [ ] Tests

        * [ ] Benchmarks

    * [ ] Clustering | Multi-Threading

        * [ ] Tests

        * [ ] Benchmarks

* [ ] Syntax Support

    * [ ] Callbacks

    * [ ] Promises

    * [ ] Streaming

    * [ ] Async/Await

* [ ] Math Support

    * [ ] Big Numbers

    * [ ] Small Numbers

## Patrons

[![Carrot's Patrons](https://img.shields.io/endpoint.svg?color=blue&label=patrons&logo=patrons&url=https%3A%2F%2Fshieldsio-patreon.herokuapp.com%2Fliquidcarrot)](https://www.patreon.com/liquidcarrot)

[![Become a Patron](https://c5.patreon.com/external/logo/become_a_patron_button.png)](https://www.patreon.com/liquidcarrot)

## Acknowledgements

A special thanks to:

[@wagenaartje](https://github.com/wagenaartje) for [Neataptic](https://github.com/wagenaartje/neataptic/) which was the starting point for this project

[@cazala](https://github.com/cazala) for [Synaptic](https://github.com/cazala/synaptic/) which pioneered architecture free neural networks in javascript and was the starting point for Neataptic

[@robertleeplummerjr](https://github.com/robertleeplummerjr) for [GPU.js](https://github.com/gpujs/gpu.js) which makes using GPU in JS easy and [Brain.js](https://github.com/BrainJS/brain.js) which has inspired Carrot's development