TensorFlow.js: Machine Learning for the Web and Beyond


TensorFlow.js: machine learning for the web and beyond Smilkov et al., SysML’19

If machine learning and ML models are to pervade all of our applications and systems, then they’d better go to where the applications are rather than the other way round. Increasingly, that means JavaScript – both in the browser and on the server.

TensorFlow.js brings TensorFlow and Keras to the the JavaScript ecosystem, supporting both Node.js and browser-based applications. As well as programmer accessibility and ease of integration, running on-device means that in many cases user data never has to leave the device.

On-device computation has a number of benefits, including data privacy, accessibility, and low-latency interactive applications.

TensorFlow.js isn’t just for model serving, you can run training with it as well. Since its launch in March 2018, people have done lots of creative things with it. And since it runs in the browser, these are all accessible to you with just one click!

Read more at the morning paper