Subtly wrong ideas are much more dangerous to progress in science than plainly wrong ideas. Some subtly wrong ideas seem to include mirror neurons, integrated information theory, the gut brain, the extended mind and autopoiesis.
Replying to @ivan_aksamentov
I think of conv nets as a solution to solve the problem of multiple feature instantiation in the context of a feed forward paradigm of function approximation. They seem to work quite well for certain problems.
12:58 PM - 26 Mar 2019
from Stanford, CA
0 replies
0 retweets
2 likes
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.