The Machine Learning Toolkit for JavaScript

JSMLT. An open-source easy-to-use machine learning library. Programmed entirely in JavaScript. We've got supervised learning, right inside your browser! And what's even better: we've got interactive, 2-dimensional visualizations of all classical machine learning algorithms, ready for use — why not take it for a spin straight away?

Try the JSMLT interactive demo

Getting started

Installing JSMLT is really, really easy! It's available on npm, so to use it in your project you only have to run:

npm install @jsmlt/jsmlt

A simple classifier

Now that JSMLT is installed, you're ready to run your first machine learning scenario! In this example, we'll train a linear SVM on some dummy data, and make some predictions! All in all, we just need a few lines of code for this:

// Import JSMLT library
var jsmlt = require('@jsmlt/jsmlt');

// Training data
train_X = [[-1,-1], [-1,1], [1,1], [1,-1]];
train_y = [0, 0, 1, 1];

// Testing data
test_X = [[1,2], [1,-2], [-1,-2], [-1,2]];

// Create and train classifier
var clf = new jsmlt.Supervised.SVM.SVM({
  kernel: new jsmlt.Kernel.Linear(),
});
clf.train(train_X, train_y);

// Make predictions on test data
console.log(clf.predict(test_X));

Running this code will output the predictions for our 4 test data points:

[ 1, 1, 0, 0 ]

The entire npm package for running this code is available in the JSMLT examples repository. Clone it & run it!