this icon 
is arguably an abstraction of an airplane, but tells us little about how airplanes work
this icon 
doesn’t tell us how brains work & is not constrained by how brains work
deep nets may prove to be more like icons than bona fide, empirically useful neural modelshttps://twitter.com/timos_m/status/1200429999251169283 …
-
This is silly. You can include the complexity within the transfer function or elsewhere if ypu neednit. I am pretty sure that important bits are missing from oir neural theories, but mocking a model for the way it looks ignores what models are for and the nature of science.
Whether this is prescient or merely funny is still unknown. Some details we omit will just be housekeeping that we can safely ignore, but other things that we don't yet grasp may ultimately radically change our understanding in ways that render all current models obsolete
-
-
Example- when I was in graduate school, glia didn't do anything but hold all that stuff together. Well, at least according to what we -thought we knew- it did.
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.