Machine Learning in JavaScript (TensorFlow Dev Summit 2018)

Nikhil Thorat and Daniel Smilkov introduce TensorFlow.js for training and deploying machine learning models directly in the browser.

Nikhil Thorat and Daniel Smilkov discuss TensorFlow.js, which is TensorFlow’s new machine learning framework for JavaScript developers. It supports building ML models in JavaScript, and training and deploying them in browser for execution using WebGL. They focus on tensorflow.js-Core which is a rebranding of deeplearn.js, and a new high-level layers API to make it easier to develop ML models in JavaScript. Initial set of converters for converting saved TF models into JS is also being released. Visit the site → js.tensorflow.org/ Check out the blog for an article on Machine Learning in JavaScript → medium.com/tensorflow/ TensorFlow Dev Summit 2018 All Sessions playlist → goo.gl/Lsaq1R Subscribe to the TensorFlow channel → goo.gl/ht3WGe event: TensorFlow Dev Summit 2018; re_ty: Publish; product: TensorFlow - TensorFlow JS; fullname: Nikhil Thorat, Daniel Smilkov; event: TensorFlow Dev Summit 2018;