Deep learning is to biological neural systems as quantum theory is to consciousness. @KordingLab @tyrell_turing @tdverstynen @GaryMarcus @GaryMarcus @danilobzdok @kendmil
-
I'm sorry, but this is a bad take. Yes, we know they are simplifications of real brains. 1) Neurons do something very similar to linear integration with a non-linearity. 2) They process inputs in a distributed, parallel manner. ANNs capture this basic process, period.
1 & 2 are vague but true for some aspects of the brain, possibly not all, but at best only part of an answer. if you had something analogous to an alternator for a car, would that in itself mean that your alternator analogue captures the dynamics of an internal combustion engine?
-
-
Okay, I'm not sure what you're not getting here. My claim is simply that there are aspects of neural computation that ANNs capture. That is a fact, not a hypothesis. Why are we even debating this?
-
because we don't know relation between those aspects & how neural computation as whole works. all we have is approximation to something that itself could be misinterpreted. approximation might be wrong in important ways, & we could be off on the role is of the approximated thing
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.