The arguments about symbolic vs deep learning for AI reminds me a lot of arguments about numerical methods vs ML for solving physics problems. Seems like hybrid methods are the way to go in both cases.
Deep Learning Is Hitting a Wall. What would it take for artificial intelligence to make real progress?
#longread
in
@NautilusMag
on one of the key technical questions in AI.
Perhaps I should roll this back a little bit, since I'm still not entirely sure exactly what "symbolic AI" means. Here I was taking it to mean algorithms based on human reasoning.
@shoyer
@GaryMarcus
DL methods are already haphazardly hybrid… there is a lot of meta programming/control loops that are written in symbolic programming languages…