Great critique of #DeepLearning includes insightful anecdote: @GaryMarcus trained a NN identity function f(x) = x on even numbers (in binary vector representation); testing worked on even numbers but not odd numbers! NN couldn't extrapolate beyond the training space.https://twitter.com/GaryMarcus/status/948364570120335363 …
-
I agree i.i.d. is very restrictive, but taking a procedure built within the i.i.d. framework and hoping that it might do something extra-i.i.d. is ... wishful thinking.
agreed. But my point is that the field does a lot of wishful thinking when it imagines that problems like natural language understanding can be solved with IID techniques that are really are inappropriate tools. Human language learning is clearly using something different.
-
-
Definitely agree about wishful thinking. But if you have enough people banging on keyboards, something interesting might come out of it... I'm just keeping my eyes open.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
It's based on human interaction and now it's proved
- http://blog.italki.com/wp-content/uploads/2017/12/italki2018FinalReport.pdf … -
tl;dr.
End of conversation
New conversation -
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.