Interestingly, they initialise the visual learning model using the ImageNet images. Was it 3 years ago that was considered a pretty much intractable problem, and now the fact a CNN can work on it well enough to be useful isn’t even worth a complete sentence.
A comment about some more deep learning feats:
(Background on ImageNet recent progress: http://lesswrong.com/lw/lj1/open_thread_jan_12_jan_18_2015/bvc9 )