Re:Major advancements in Deep Learning in 2016
by amelius on Wednesday December 07, 2016 @04:07PM
(#13126221)
Perhaps we're on a plateau with good real-life applications then :)
Re:Major advancements in Deep Learning in 2016
by paulbaumgart on Wednesday December 07, 2016 @07:38PM
(#13127533)
Probably true for the "internet scale" applications. But my impression is that there's still lots of medium-sized opportunities to build interesting things around the edges, in fields outside of the mobile/PC ecosystem.
Re:Major advancements in Deep Learning in 2016
by miketery on Wednesday December 07, 2016 @11:41PM
(#13128448)
What are some tools, frameworks, or platforms that you enjoy or recommend (for starters)?
Re:Major advancements in Deep Learning in 2016
by tshadley on Saturday December 10, 2016 @06:58PM
(#13148706)
Here's a chart:
https://en.wikipedia.org/wiki/Comparison_of_deep_learning_so...
I'd recommend starting with Theano, Tensorflow, anything python. I do like Torch's raw speed on CUDA though.
It may be different for other reasons but the main difference I note today is the number of opensource AI/ML platforms that are trivial to install, use, play, experiment at pretty much near the peak computing capacity of the hardware we use today. Exploring the vast search space of reality has never been easier and faster than today.