“[Marcus 2012] is the first place where anybody said that deep learning ... wouldn’t be a panacea,” @GaryMarcus https://link.medium.com/XsEiDj7ZjS
Maybe you really don't know that that is the default belief by almost everyone. See a whole 1992 bookhttps://books.google.com/books/about/The_Symbolic_and_Connectionist_Paradigms.html?id=uAtWCpHoUxMC&printsec=frontcover&source=kp_read_button#v=onepage&q&f=false …
-
Yes, the gap between symbolic and connectionist paradigms is a very old problem. The early 90's was that previous time when connectionist methods made a come back.
-
-
In 1999,
@DaveTouretzky asked on the connectionist mailing list "Is connectionist symbol processing dead?" The result comments were assembled into a thoughtful collection. I wonder if the responses would be any different today? https://www.researchgate.net/publication/2448811_Connectionist_Symbol_Processing_Dead_or_Alive …pic.twitter.com/vOeR2fOZJo
-
And despite the public hostility Hinton displayed in 2015 in his “aetherial symbols” talk at Stanford.
End of conversation
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.