https://github.com/matiasvlevi/Dann

Deep Neural Network Library for JavaScript.
https://github.com/matiasvlevi/Dann

dann dannjs deep-learning deep-neural-networks javascript js machine-learning neural-network nodejs

Last synced: 9 days ago
JSON representation

Deep Neural Network Library for JavaScript.

• Host: GitHub
• URL: https://github.com/matiasvlevi/Dann
• Owner: matiasvlevi
• License: mit
• Archived: true
• Created: 2020-09-04T17:59:49.000Z (almost 4 years ago)
• Default Branch: master
• Last Pushed: 2022-11-01T03:48:38.000Z (over 1 year ago)
• Last Synced: 2024-06-19T02:09:00.379Z (9 days ago)
• Topics: dann, dannjs, deep-learning, deep-neural-networks, javascript, js, machine-learning, neural-network, nodejs
• Language: JavaScript
• Homepage: https://dannjs.org
• Size: 3.57 MB
• Stars: 427
• Watchers: 8
• Forks: 23
• Open Issues: 7
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGES.md
  • Contributing: CONTRIBUTING.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE

Lists

• awesome-github-star - Dann

README

        



  

    

  





        



Deep Neural Network Library for Javascript



    Train a neural network with your data & save its trained state!

  





  Demo •

  Installation •

  Documentation •

  Contribute •

  Discord •

  License






## Installation

### CDN :

```html

```

### Node :

```

npm i dannjs

```

[dannjs on npmjs.com](https://www.npmjs.com/package/dannjs)





## Getting started

### Require package

Components from the library can be imported like this

```js

const { Dann } = require('dannjs');

 ```




### Basic model construction

Setting up a small (4,6,6,2) neural network.

```js

const nn = new Dann(4, 2);

nn.addHiddenLayer(6, 'leakyReLU');

nn.addHiddenLayer(6, 'leakyReLU');

nn.outputActivation('tanH');

nn.makeWeights();

nn.lr = 0.0001;

nn.log({details:true});

```




### Train by backpropagation

Training with a dataset.

```js

//XOR 2 inputs, 1 output

const dataset = [

    {

        input: [0, 0],

        output: [0]

    },

    {

        input: [1, 0],

        output: [1]

    },

    {

        input: [0, 1],

        output: [1]

    },

    {

        input: [1, 1],

        output: [0]

    }

];

//train 1 epoch

for (data of dataset) {

    nn.backpropagate(data.input, data.output);

    console.log(nn.loss);

}

```




### Train by mutation

For neuroevolution simulations. Works best with small models & large population size.

```js

const populationSize = 1000;

let newGeneration = [];

for (let i = 0; i < populationSize; i++) {

    // parentNN would be the best nn from past generation.

    const childNN = parentNN;

    childNN.mutateRandom(0.01, 0.65);

    newGeneration.push(childNN);

}

```




### Standalone function

Convert a Neural Network to a JS function that can output predictions without the library.

```js

let strfunc = nn.toFunction();

console.log(strfunc);

```




### Save JSON

```js

let json = nn.toJSON();

console.log(json);

```







### Demo:

[AI predicts San-francisco Housing prices.](https://dannjs.org/livedemo.html) 


more examples & demos [here](https://dannjs.org/#exm)




### Online editor:

[https://dannjs.org/sandbox](https://dannjs.org/sandbox)




### Socials


























### Graph Dann models with this library

[Dann-p5](https://github.com/matiasvlevi/Dann-p5)




### Stickers

[Get Dannjs stickers!](https://www.redbubble.com/people/Dannjs/shop)





 

## Contributors

  

    
Matias Vazquez-Levi
💻 📖 ⚠️ ✅

    
Francesco Ciulla
📢

    
Labnan
🐛 💻 ⚠️

    
sharkAce
💻

    
Hasnain Iqbal
💻 ⚠️

    
EL Ramos
🐛 ⚠️ 💻

    
viabhinav
✅

  

  

    
and1can
💻 ⚠️

  




Any contributions are welcome! See [CONTRIBUTING.md](https://github.com/matiasvlevi/Dann/blob/master/CONTRIBUTING.md).








## License

MIT