Hacker News new | past | comments | ask | show | jobs | submit login
A hardware-accelerated machine intelligence library for the web (pair-code.github.io)
59 points by _pfwi on Aug 11, 2017 | hide | past | favorite | 7 comments



Here's the associated Google Research Blog post:

https://research.googleblog.com/2017/08/harness-power-of-mac...


Tl;dr Tensorflow and numpy-like API. Differs from tensorfire in that it can also do backprop (training)


http://playground.tensorflow.org/ is fun and worth looking at.

As I recall, Google created it to give their engineers an introductory feel for DL, and then open sourced it.


It looks like this is the easiest way to train neural networks with GPU acceleration on my Radeon Pro (i.e. non CUDA)...

Thank you JavaScript!


"Currently our demos do not support Mobile, Firefox, and Safari. Please view them on desktop Chrome for now." That's a bummer.


This will be fixed in ~2 weeks, max.


Url changed from https://github.com/PAIR-code/deeplearnjs, which points to this.




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: