![NiMA 🤖🧠🌊[0.8.5]](https://pbs.twimg.com/profile_images/1130181150624899074/fF13D7Q5_normal.png)
My claim is that you have robustly criticized an all-sub-symbolic approach.
No, @tdietterich, this is a serious misrepresentation. Saying we need hybrids doesn’t mean I see no role for subsymbolic computation. Have never ever said such a thing.https://twitter.com/tdietterich/status/1143633192944979968 …
-
-
-
that part is correct
- 1 more reply
New conversation -
-
-
To a certain extent these are reified distinctions. You cannot put any instruction into our current computing systems that isn’t some weird subsymbolic thing. But at the same time it’s our interpretation or the expression coming out that’s symbolic.
-
E.g: while computer algebra systems are “symbolic” they actually do get shoved down into numerically bounded hardwares. And when we read info out or have a system do something in the world it’s expressed to a human or some object in the world symbolically/metaphorically/analog.
- 1 more reply
New conversation -
-
-
Metaphors are expressions for inductive bias..
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.