Tom is exactly right, actually.
this thread by @tdietterich blurs many distinctions and misrepresents my views, especially with respect to differentiable programming. reply (somewhat technical) forthcoming, perhaps next week.https://twitter.com/tdietterich/status/948811917593780225 …
-
-
- 1 more reply
New conversation -
-
-
You wrote on your critical appraisal about differential computers, implying that the approach was somewhat different from deep learning. Yes, DL has problems, but have we seen any better alternatives? Probably only imaginary ones.
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.