Great! New thread then: What are the ways in which people in the neural net community think that today's ANN's are NOT perfect models of the brain? Where do you want to dig deeper, and why?https://twitter.com/timkietzmann/status/1200159447651438592 …
-
It's very careful and avoids backprop. It aims to capture some of the connectivity changes in a finch brain during song learning, and replicates the conditions of the task carefully. That's the main way I've seen ANNs used as neurological models. Maybe I've been lucky.
if there is no backprop it may not fall under the umbrella of what many here are describing as ann’s.
-
-
I've mostly seen non-backprop models. But I've only grazed the field of neurology myself.
- 5 more replies
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.