Right. The problem is the imperialism of deep learning pioneers, eg Lecun et al 2015 Nature, which called for replacing “rule-based manipulation of symbolic expressions with operations on large vectors”. Such a strident view is antithetical to hybrid models.https://twitter.com/guyvdb/status/1065343581831852032 …
-
Criticism is helpful in remind us of our blind spots and bring fresh perspective. But beyond a certain level, it just get repetitive and meaningless. At the end of the day, doing the work and showing result trumps all.
Dont disagree, but sometimes the tools need to be reaimed or reinvented, and it’s hard to know when to do that, without first taking stock. The leading idea in science & engineering at any given moment is not always the best one. Important to know whether we are on right track.
-
-
Why is it important? Throughout history, often those who make breakthroughs did NOT care about what the scientific consensus at the time and they don't so complain or care about current set of tools, they invent what they need to advance their ideas forward
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.