What constitutes an empirically useful model? Because ANNs can make empirical predictions of brains. Is it just that you don't find these useful?
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 …
-
-
-
Which predictions?
- 2 more replies
New conversation -
-
-
What is your view on the work done by Geoff Hinton and Numenta? As in the research approach on HTM?
-
i think you mean Jeff Hawkins
- 3 more replies
New conversation -
-
-
On the left side is a biological neural “network” by Cajal (circa 1899) compared to an ANN on the right ... At least
icon actually looks like a plane :)pic.twitter.com/Z7smKKjyZ2
- 3 more replies
New conversation -
-
-
what if you replace the word "brains" with "small populations of neurons" or "in vitro-neuronal cultures"? because ANN can describe those quite well, in particular SNNs with local learning etc.
-
I would actually be more comfortable with that, with all the usual concerns about in vitro not necessarily being a good model of in vivo applying.
- 1 more reply
New conversation -
-
-
I’ve got the exact thing right here!pic.twitter.com/FtxqiT5vFx
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.