Wondering if it’s worthwhile to figure out whether and how “deep learning” is bogus. Seems MUCH too good to be true: http://www.technologyreview.com/view/530561/the-revolutionary-technique-that-quietly-changed-machine-vision-forever/ …
I’d guess that dataset has non-object-type regularities that the “neural” network is exploiting, and the researchers are fooling themselves.
2:09 AM - 15 Sep 2014
0 replies
0 retweets
1 like
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.