Deeplearn.js opens up ML in Web Browsers - Archived
Machine learning is gloriously deepening in its scheme of affairs with Google releasing its latest opensource offering of hardware accelerated libraries that runs in a browser.
Personalisation just moved to a much higher level with this new “old kid ?” on the block. Google’s latest desktop variant of Chrome (Ver. 62.0 and up) supports the libraries as the project sees to capture more device and hardwares in the coming times.
The Deeplearn.js library enables training of neural networks within a browser without any software installation or back-end works.
“A client-side ML library can be a platform for interactive explanations, for rapid prototyping and visualization, and even for offline computation,”
A researchers from Google says;
“And if nothing else, the browser is one of the world’s most popular programming platforms.”
Deeplearn.js imitates the structure of Google’s TensorFlow machine intelligence library and NumPy, a scientific computing package based on Python.
“We have also implemented versions of some of the most commonly used TensorFlow operations. With the release of Deeplearn.js, we will be providing tools to export weights from TensorFlow checkpoints, which will allow authors to import them into webpages for Deeplearn.js inference.”
Hey, u know something, Seems like ML is not leaving any time soon.