Sounds like you're describing this:https://www.sciencemag.org/news/2018/05/ai-researchers-allege-machine-learning-alchemy …
Deep learning isn't a science, but rather an ever-changing set of empirically-derived engineering best practices, woven together by over-claiming, unreliable narratives.
-
-
-
Pssssst! As long as the emperor is happy with his new clothes why spoil the party?
End of conversation
New conversation -
-
-
Actually, that *does* sound a lot like science.
- Show replies
New conversation -
-
-
You need to work "heuristics" in there and you've got yourself an abstract.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Then is the field now better suited to experimental physicist rather than theoretical ones?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Like most graph-fitting do when data points changes. Except adding in some extrema mathematical sophistication spiced it up and elevated it to scientific status
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
mandar pro pessoal que tá entrando nas graduações em "ciência de dados"
- Show replies
New conversation -
-
the narratives keep changing :) has a conclusion been reached on why batch normalisation works? every 6 months there is a different story....
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.