|
@Zergylord | |||||
|
Aristotelian physics may be flawed, but it has been unfairly discarded in favor of Newtonian physics, despite the latter not solving all of the open problems in the field. Clearly the way forward is a hybrid system, wherein aether obeys the conservation of momentum. #AIDebate pic.twitter.com/ZgNpoaqTi7
|
||||||
|
||||||
|
Edward Grefenstette
@egrefen
|
30. pro |
|
This is some top-class trolling, but after a chuckle it has mostly just reminded me how much I wish I could ignore both the AI debate thing and the whole symbolic-DL “war” on Twitter.
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
30. pro |
|
100% agree. Felt guilty contributing to it, but justified it by reassuring myself that having too much pent-up snark is unhealthy.
P.S. Wish you were still at DeepMind so I could get "top-class trolling" on my next performance review ;)
|
||
|
|
||
|
Vahid Kazemi
@VahidK
|
30. pro |
|
The more interesting question is what are you doing still at NeurIPS 2019? Are the after parties still going?
|
||
|
|
||
|
Steven Hansen
@Zergylord
|
30. pro |
|
NeurIPS 2019 lives on in all of our hearts!
... And in the Twitter bio of the forgetful
|
||
|
|
||
|
Leonid Boytsov
@srchvrs
|
30. pro |
|
Nothing has been discarded. The industry uses much more of the old stuff as well as hybrids than deep learners would like to admit. Of course, possibilities are endless, but as of now, a lot of this is vaporware.
|
||
|
|
||
|
Leonid Boytsov
@srchvrs
|
30. pro |
|
And don't get me wrong: certainly deep learning is very useful (and I have been using it increasingly more often). However, I, e.g., have at least one problem where pure DL isn't useful, so when I hear they will solve everything with attention.
|
||
|
|
||
|
Olivier Codol
@OlivierCodol
|
30. pro |
|
I thought Einstein proved Newton was wrong?
|
||
|
|
||
|
Sri Krishna
@skrish_13
|
30. pro |
|
😂
|
||
|
|
||