...But they have existed for a very long time: since the early 90s for Q1 and since the early 80s for Q2. Now that the DL machinery works, and that so many people are working on both Qs, we have a shot at making real progress.
-
Deep learning, in principle, provides grounding for the semantics of internal representations that current symbolic methods lack. Other learning approaches might do this too. 3/
But not for compositionality or causal reasoning in any obvious way (cc @yudapearl)
-
-
I wish I could join this discussion but I can't parse Tom's "DL provides grounding for the semantics of internal representations that current symbolic methods lack." In my simple world, it is symbolic representation that provides semantics, not DL. What am I missing?
-
@yudapearl makes a really good point here, but crucially i think he is referring to what I would call sentence-level semantics; the stuff@tdietterich is talking about is at the level of individual symbols. deep learning might help there, but not with what Judea rightfully seeks. - 1 more reply
New conversation -
-
-
Could you clarify the compositionality <=> AGI relationship? It's clear that compositionality has practical use for semantics, but wouldnt demand for compositionality be tempered since at a general level it breaks down with certain types of propositions - sensation language, etc
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.