top | item 14992865 A hardware-accelerated machine intelligence library for the web 59 points| obulpathi | 8 years ago |pair-code.github.io | reply 7 comments order hn newest [+] [-] gradys|8 years ago|reply Here's the associated Google Research Blog post:https://research.googleblog.com/2017/08/harness-power-of-mac... [+] [-] dgacmu|8 years ago|reply Tl;dr Tensorflow and numpy-like API. Differs from tensorfire in that it can also do backprop (training) [+] [-] mncharity|8 years ago|reply 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. [+] [-] mamp|8 years ago|reply 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! [+] [-] xamlhacker|8 years ago|reply "Currently our demos do not support Mobile, Firefox, and Safari. Please view them on desktop Chrome for now." That's a bummer. [+] [-] nsthorat|8 years ago|reply This will be fixed in ~2 weeks, max. [+] [-] dang|8 years ago|reply Url changed from https://github.com/PAIR-code/deeplearnjs, which points to this.
[+] [-] gradys|8 years ago|reply Here's the associated Google Research Blog post:https://research.googleblog.com/2017/08/harness-power-of-mac... [+] [-] dgacmu|8 years ago|reply Tl;dr Tensorflow and numpy-like API. Differs from tensorfire in that it can also do backprop (training)
[+] [-] dgacmu|8 years ago|reply Tl;dr Tensorflow and numpy-like API. Differs from tensorfire in that it can also do backprop (training)
[+] [-] mncharity|8 years ago|reply 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.
[+] [-] mamp|8 years ago|reply 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!
[+] [-] xamlhacker|8 years ago|reply "Currently our demos do not support Mobile, Firefox, and Safari. Please view them on desktop Chrome for now." That's a bummer. [+] [-] nsthorat|8 years ago|reply This will be fixed in ~2 weeks, max.
[+] [-] dang|8 years ago|reply Url changed from https://github.com/PAIR-code/deeplearnjs, which points to this.
[+] [-] gradys|8 years ago|reply
https://research.googleblog.com/2017/08/harness-power-of-mac...
[+] [-] dgacmu|8 years ago|reply
[+] [-] mncharity|8 years ago|reply
As I recall, Google created it to give their engineers an introductory feel for DL, and then open sourced it.
[+] [-] mamp|8 years ago|reply
Thank you JavaScript!
[+] [-] xamlhacker|8 years ago|reply
[+] [-] nsthorat|8 years ago|reply
[+] [-] dang|8 years ago|reply