meanwhile, @ylecun your 2015 nature paper seemed in its last paragraph to dismiss symbolic knowledge, contra your tweet. is this a change in view? hooray if yes! 2/2
Show this thread
@ylecun i absolutely do not dismiss gradient based learning (as part of larger system) & have said so publicly and to you privately. please read deep learning: a critical appraisal, particularly parts about deep learning as tool of larger system, and stop misrepresenting me. 1/2https://twitter.com/ylecun/status/1065837329221328896 …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
As I, Geoff, Léon Bottou and others have said: "replace symbols by vectors and logic by algebra". This does not preclude reasoning, or even variable binding. But it may make reasoning differentiable. Read Leon's "from ML to Machine Reasoning". Call it symbolic or not, no matter.
-
what does variable binding mean in this context? if you can find a space for variable binding in your world, I am interested.
End of conversation
New conversation -
-
-
As
@dileeplearning and Vicarious have shown, 0-shot gen & forward planning can be learned using the work of@yudapearl. It requires grounding indicators to graphical models. So next, create a multi-agent symbol grounder guided by objectives, or use brute force.@IntuitMachineThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
In 1987, I went from Tech to the 1st IJCNN. It was an unnerving world of backstabbing and grant-seeking. Changed my life: I left AI and NN work for 25 yrs bc of it. Sad to see it again on this thread.
#aiwinter is coming. Cc@Grady_Booch@filippie509pic.twitter.com/IQ7TX50cop
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.