Dear #deeplearning fans,
The critical question, as I have said, over and over again, is not whether deep learning is useful, it's whether or not we need to move towards hybrids.
You can't keep portraying hybrids as pure deep learning systems, and claim to have won the argumenthttps://twitter.com/GaryMarcus/status/1184460444037025792 …
-
-
I wish researchers and practitioners would stop using words like learning and knowledge in context of ML/AI in particular when human intelligence is mentioned in the same tweet
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
When you say "symbolic representation", do you think the way forward is a symbolic representation of the hacks required for DL to work. A programmable grammar for the various "inductive biases" and "training procedures" required to get DL to work on a broad class of problems?
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.