There seem to be an academic collective memory half-life of research results/articles of about 20 - 30 yrs or so and then it starts repeating (with of course some variations) ...
People who don’t know history are doomed to say ignorant things about it. Here’s a neural network model of sentence comprehension, once widely cited, from 30 years ago. People have been working on this for a long time. https://www.tandfonline.com/doi/abs/10.1080/01690968908406371 …https://twitter.com/LanguageMIT/status/1056865214568763392 …
-
-
-
recently cut to 6 years.
End of conversation
New conversation -
-
-
Pretty ridiculous to suggest that Ted Gibson "doesn't know history." And how does 1989 paper invalidate the claim that a vast majority of the surge of interest (+compute) in modern DL has focused on easier problems? (object/speech recognition, surface-level/"cheatable" NLP tasks)
-
obviously ted know his history. i am concerned for the unnamed people who run his lab twitter account and claim that deep learning only started study compositionality recently. that’s just wrong. another example is all of elmans highly cited work in the 90s.
End of conversation
New conversation -
-
-
One could argue that, it seems to be much easier for most of us to discuss things we don’t know about or understand than what we do know or do understand. Of course, the world would be more silent place if we could only discuss what we truly know or understand
#SedatephobiaThanks. 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.