The 2014 ImageNet results are spectacular though, and do seem probably *somewhat* similar to mammalian visual processing.
This isn’t new at all. Machine learning has been doing this since the 1950s.
-
-
1950s ML didn't replace the other, more knowledge-intensive approaches the way DL is replacing them now, nor be capable of doing as much.
-
The DL algorithms are little changed from mid-80s backprop which we ran on 1MHz processors. The main difference is GPU power. Brute force.
- 9 more replies
New conversation -
-
-
Relevant, from http://catb.org/jargon/html/koans.html … . Story may not be exactly accurate, but broadly reflective. MIT-AI PDP-6 decommissioned ~1976.pic.twitter.com/11nbKg9EV8
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.