It probably needs to be more empirical.
Did you see his NIPS talk and the reply? https://medium.com/@Synced/lecun-vs-rahimi-has-machine-learning-become-alchemy-21cb1557920d …
-
-
When I said "empirical," I didn't mean blind trial and error. But never mind, totally agree that "lack of theoretical understanding or technical interpretability of machine learning models is cause for concern."
-
Feel free to elaborate!
-
In vision science, for example, people are lackadaisical about creating functional models w/out having any knowledge/understanding of the natural phenomena they're supposed to be modelling. So they fail empirically, b/c to succeed empirically you actually need to think.
-
I didn't know vision models were so bad typically. I don't read that literature often at all.
-
They're beyond hopeless.
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.