A hardware-accelerated machine intelligence library for the web

Here&#x27;s the associated Google Research Blog post:<p><a href="https:&#x2F;&#x2F;research.googleblog.com&#x2F;2017&#x2F;08&#x2F;harness-power-of-machine-learning-in.html" rel="nofollow">https:&#x2F;&#x2F;research.googleblog.com&#x2F;2017&#x2F;08&#x2F;harness-power-of-mac...</a>

<a href="http:&#x2F;&#x2F;playground.tensorflow.org&#x2F;" rel="nofollow">http:&#x2F;&#x2F;playground.tensorflow.org&#x2F;</a> is fun and worth looking at.<p>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)...<p>Thank you JavaScript!

&quot;Currently our demos do not support Mobile, Firefox, and Safari. Please view them on desktop Chrome for now.&quot; That&#x27;s a bummer.

Url changed from <a href="https:&#x2F;&#x2F;github.com&#x2F;PAIR-code&#x2F;deeplearnjs" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;PAIR-code&#x2F;deeplearnjs</a>, which points to this.