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 …
-
-
Ignoring the essentially only positive examples, scarce feedback. How about: Conscious processes are ~100 bits/sec. To learn to read by spending 5 hrs/day for 3 years is then max 250MB consciously processed for the task (not all necessary reading letters). But this is fraught as
-
there are questions like how much unconscious processing is done and how much time is devoted to it? It clearly can't be 100% and it's unlikely to be long. This is why I preferred to talk about energy (not time). It is much easier to delineate upper-bounds & cleanly compare there
- 19 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.