I have a prepreprint on relationship between deep neural networks and cortical pathways. Will link you when done!
This all being said though the concept of what is and not "natural" or "biological" or even dirtier words like 1/2
-
-
"neuroplausible" is not simple to pin down because they're often incoherent. Altho see: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.155.793&rep=rep1&type=pdf …
-
At the end of the day if you are on the e.g., computational level and you perform an appropriate computation 1/2
-
with your model then your model is indeed *insert one of those weasel words*. 2/2 https://en.wikipedia.org/wiki/David_Marr_(neuroscientist)#Levels_of_analysis …
-
Final thought: I teach ANNs and I plan to do some outreach stuff for lay ppl so I might ask you for feedback.
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.