TensorFire Brings Machine Learning to Webpages

By HTMLGoodies Staff


Building the Right Environment to Support AI, Machine Learning and Deep Learning

A team of MIT graduate students have released a new JavaScript library called TensorFire that makes it possible to run machine learning models from within a browser. Based on Google's TensorFlow technology, TensorFire uses the hardware-accelerated graphics APIs in modern browsers to set up neural networks on any GPU. Importantly, it doesn't require the end user to download or install anything, and performance is fast.

To demonstrate how the technology might be used on a website, the team set up a site that can map a piece of artwork to another image.

The developers plan to release TensorFire under an open source MIT license.

View article

Make a Comment

Loading Comments...

  • Web Development Newsletter Signup

    Invalid email
    You have successfuly registered to our newsletter.

    By submitting your information, you agree that htmlgoodies.com may send you HTMLGOODIES offers via email, phone and text message, as well as email offers about other products and services that HTMLGOODIES believes may be of interest to you. HTMLGOODIES will process your information in accordance with the Quinstreet Privacy Policy.

Thanks for your registration, follow us on our social networks to keep up-to-date