Both ANNs and brains are (1) highly distributed and parallel (2) make small changes (3) efficient. Ideas like generalization hold for all systems with these three properties. In that sense, @tyrell_turing is obviously right. Maybe @GaryMarcus uses narrow def of abstraction.https://twitter.com/GaryMarcus/status/1200088188934451200 …
-
-
ANNs helped us understand why binocular neurons have antagonistic RFs in each eye -- they are very informative wrt depth from binocular disparity. We even derived a closed form model out of the ANNs!https://www.sciencedirect.com/science/article/pii/S0960982217304049 …
-
And complex cells: https://www.ncbi.nlm.nih.gov/m/pubmed/12904330/ …
End of conversation
New conversation -
-
-
You don't actually keep up with the neuroscience literature, do you? That has been evident in these conversations... Here, lemme give you a few examples:
-
Not going to respond to the below given the above. You can read my recent tweet on DiCarlo if you are interested in how I think about these things. Bye for now.
- 1 more reply
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.