Machine Learning in JavaScript (TensorFlow Dev Summit 2018)




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 → https://js.tensorflow.org/
Check out the blog for an article on Machine Learning in JavaScript → https://medium.com/tensorflow/

TensorFlow Dev Summit 2018 All Sessions playlist → https://goo.gl/Lsaq1R
Subscribe to the TensorFlow channel → https://goo.gl/ht3WGe

Original source


28 responses to “Machine Learning in JavaScript (TensorFlow Dev Summit 2018)”

  1. After the brief mobile-detour, the world is moving back to web. With progressive apps, and these super interactive real-time apps, I can see using just bookmarks instead of apps on my phone. This looks promising.

Leave a Reply