Counting 2,399 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1

Project Page
Last Commit
Feb. 19, 2018
Feb. 13, 2016





brain.js is a library of Neural Networks written in JavaScript.

đź’ˇ Note: This is a continuation of the harthur/brain repository (which is not maintained anymore). For more details, check out this issue.


Here's an example showcasing how to approximate the XOR function using brain.js:

//create a simple feed forward neural network with backpropagation
var net = new brain.NeuralNetwork();

net.train([{input: [0, 0], output: [0]},
           {input: [0, 1], output: [1]},
           {input: [1, 0], output: [1]},
           {input: [1, 1], output: [0]}]);

var output =[1, 0]);  // [0.987]


//create a simple recurrent neural network
var net = new brain.recurrent.RNN();

net.train([{input: [0, 0], output: [0]},
           {input: [0, 1], output: [1]},
           {input: [1, 0], output: [1]},
           {input: [1, 1], output: [0]}]);

var output =[0, 0]);  // [0]
output =[0, 1]);  // [1]
output =[1, 0]);  // [1]
output =[1, 1]);  // [0]

However, There's no reason to use a neural network to figure out XOR. (-: So, here's a more involved, realistic example: Demo: training a neural network to recognize color contrast.

More Examples

You check out this fantastic screencast, which explains how to train a simple neural network using a real world dataset: How to create a neural network in the browser using Brain.js.



If you have node, you can install brain.js with npm:

npm install brain.js

Or if you prefer yarn:

yarn add brain.js

Alternatively, you can install brain.js with bower:

bower install brain.js

At present, the npm version of brain.js is approximately 1.0.0, featuring only Feed forward NN. All other models are beta and are being jazzed up and battle hardened. You can still download the latest, though. They are cool!


Download the latest brain.js for browser. Training is computationally expensive, so you should try to train the network offline (or on a Worker) and use the toFunction() or toJSON() options to plug the pre-trained network into your website.


Use train() to train the network with an array of training data. The network has to be trained with all the data in bulk in one call to train(). The more training patterns, the longer it will probably take to train, but the better the network will be at classifying new patterns.

Data format

Each training pattern should have an input and an output, both of which can be either an array of numbers from 0 to 1 or a hash of numbers from 0 to 1. For the color contrast demo it looks something like this:

var net = new brain.NeuralNetwork();

net.train([{input: { r: 0.03, g: 0.7, b: 0.5 }, output: { black: 1 }},
           {input: { r: 0.16, g: 0.09, b: 0.2 }, output: { white: 1 }},
           {input: { r: 0.5, g: 0.5, b: 1.0 }, output: { white: 1 }}]);

var output ={ r: 1, g: 0.4, b: 0 });  // { white: 0.99, black: 0.002 }

Here's another variation of the above example. (Note that input objects do not need to be similar.)

net.train([{input: { r: 0.03, g: 0.7 }, output: { black: 1 }},
           {input: { r: 0.16, b: 0.2 }, output: { white: 1 }},
           {input: { r: 0.5, g: 0.5, b: 1.0 }, output: { white: 1 }}]);

var output ={ r: 1, g: 0.4, b: 0 });  // { white: 0.81, black: 0.18 }

Training Options

train() takes a hash of options as its second argument:

net.train(data, {
                            // Defaults values --> expected validation
      iterations: 20000,    // the maximum times to iterate the training data --> number greater than 0
      errorThresh: 0.005,   // the acceptable error percentage from training data --> number between 0 and 1
      log: false,           // true to use console.log, when a function is supplied it is used --> Either true or a function
      logPeriod: 10,        // iterations between logging out --> number greater than 0
      learningRate: 0.3,    // scales with delta to effect traiing rate --> number between 0 and 1
      momentum: 0.1,        // scales with next layer's change value --> number between 0 and 1
      callback: null,       // a periodic call back that can be triggered while training --> null or function
      callbackPeriod: 10,   // the number of iterations through the training data between callback calls --> number greater than 0
      timeout: Infinity     // the max number of milliseconds to train for --> number greater than 0

The network will train until the training error has gone below the threshold (default 0.005) or the max number of iterations (default 20000) has been reached, whichever comes first.

By default training won't let you know how its doing until the end, but set log to true to get periodic updates on the current training error of the network. The training error should decrease every time. The updates will be printed to console. If you set log to a function, this function will be called with the updates instead of printing to the console.

The learning rate is a parameter that influences how quickly the network trains. It's a number from 0 to 1. If the learning rate is close to 0 it will take longer to train. If the learning rate is closer to 1 it will train faster but it's in danger of training to a local minimum and performing badly on new data.(Overfitting) The default learning rate is 0.3.

The momentum is similar to learning rate, expecting a value from 0 to 1 as well but it is multiplied against the next level's change value. The default value is 0.1

Any of these training options can be passed into the constructor or passed into the updateTrainingOptions(opts) method and they will be saved on the network and used any time you trian. If you save your network to json, these training options are saved and restored as well (except for callback and log, callback will be forgoten and log will be restored using console.log).

There is a boolean property called invalidTrainOptsShouldThrow that by default is set to true. While true if you enter a training option that is outside the normal range an error will be thrown with a message about the option you sent. When set to false no error is sent but a message is still sent to console.warn with the information.

Async Training

trainAsync() takes the same arguments as train (data and options). Instead of returning the results object from training it returns a promise that when resolved will return the training results object.

  let net = new brain.NeuralNetwork();
    .trainAsync(data, options)
    .then(res => {
      // do something with my trained network

With multiple networks you can train in parallel like this:

  var net = new brain.NeuralNetwork();
  var net2 = new brain.NeuralNetwork();

  var p1 = net.trainAsync(data, options);
  var p2 = net2.trainAsync(data, options);

    .all([p1, p2])
    .then(values => {
      var res = values[0];
      var res2 = values[1];
      console.log(`net trained in ${res.iterations} and net2 trained in ${res2.iterations}`);
      // do something super cool with my 2 trained networks



The output of train() is a hash of information about how the training went:

  error: 0.0039139985510105032,  // training error
  iterations: 406                // training iterations


If the network failed to train, the error will be above the error threshold. This could happen because the training data is too noisy (most likely), the network doesn't have enough hidden layers or nodes to handle the complexity of the data, or it hasn't trained for enough iterations.

If the training error is still something huge like 0.4 after 20000 iterations, it's a good sign that the network can't make sense of the data you're giving it.


Serialize or load in the state of a trained network with JSON:

var json = net.toJSON();

You can also get a custom standalone function from a trained network that acts just like run():

var run = net.toFunction();
var output = run({ r: 1, g: 0.4, b: 0 });
console.log(run.toString()); // copy and paste! no need to import brain.js


NeuralNetwork() takes a hash of options:

var net = new brain.NeuralNetwork({
  activation: 'sigmoid', // activation function
  hiddenLayers: [4],
  learningRate: 0.6 // global learning rate, useful when training using streams


This parameter lets you specify which activation function your neural network should use. There are currently four supported activation functions, sigmoid being the default:

Here's a table (Thanks, Wikipedia!) summarizing a plethora of activation functions — Activation Function


You can use this to specify the number of hidden layers in the network and the size of each layer. For example, if you want two hidden layers - the first with 3 nodes and the second with 4 nodes, you'd give:

hiddenLayers: [3, 4]

By default brain.js uses one hidden layer with size proportionate to the size of the input array.


The network now has a WriteStream. You can train the network by using pipe() to send the training data to the network.


Refer to stream-example.js for an example on how to train the network with a stream.


To train the network using a stream you must first create the stream by calling net.createTrainStream() which takes the following options:

  • floodCallback() - the callback function to re-populate the stream. This gets called on every training iteration.
  • doneTrainingCallback(info) - the callback function to execute when the network is done training. The info param will contain a hash of information about how the training went:
  error: 0.0039139985510105032,  // training error
  iterations: 406                // training iterations


Use a Transform to coerce the data into the correct format. You might also use a Transform stream to normalize your data on the fly.



var likely = require('brain/likely');
var key = likely(input, net);

Likely example see: simple letter detection

Neural Network Types

Why different Neural Network Types?

Different neural nets do different things well. For example:

  • A Feedforward Neural Network can classify simple things very well, but it has no memory of previous actions and has infinite variation of results.
  • A Recurrent Neural Network remembers, and has a finite set of results.

Get Involved!


If you have an issue, either a bug or a feature you think would benefit your project let us know and we will do our best.

Create issues here and follow the template.

Latest Releases
 Feb. 11 2018
 Feb. 2 2018
 Jan. 26 2018
 Jan. 19 2018
 Jan. 14 2018