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 :

<scriptsrc="https://cdn.jsdelivr.net/gh/matiasvlevi/dann@v2.4.0/build/dann.min.js"></script>

Node :

npm i dannjs

dannjs on npmjs.com

Getting started

Require package

Object types from the library can be imported like this

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

Basic model construction

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

constnn=newDann(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.

//XOR 2 inputs, 1 outputconstdataset=[{input: [0,0],output: [0]},{input: [1,0],output: [1]},{input: [0,1],output: [1]},{input: [1,1],output: [0]}];//train 1 epochfor(dataofdataset){nn.backpropagate(data.input,data.output);console.log(nn.loss);}

Train by mutation

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

constpopulationSize=1000;letnewGeneration=[];for(leti=0;i<populationSize;i++){// parentNN would be the best nn from past generation.constchildNN=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.

letstrfunc=nn.toFunction();console.log(strfunc);

Save JSON

letjson=nn.toJSON();console.log(json);

Demo:

AI predicts San-francisco Housing prices.
more examples & demos here

Online editor:

https://dannjs.org/sandbox

Socials

Graph Dann models with this library

Dann-p5

Stickers

Get Dannjs stickers!

Contributors

Matias Vazquez-Levi 💻📖⚠️✅

Francesco Ciulla 📢

Labnan 🐛💻⚠️

sharkAce 💻

Hasnain Iqbal 💻⚠️

EL Ramos 🐛⚠️💻

viabhinav ✅

Any contributions are welcome! See CONTRIBUTING.md.

License

MIT