What is the piece about abstraction that category theory lacks?
-
-
-
Was wondering this myself. Kind of hoping the response is more arrows.
End of conversation
New conversation -
-
-
I think there's low-hanging fruit in cognitive semantics such as usage-based approaches to grammar, conceptual metaphor etc. And DL/RL work has progressed on basic situated agents to where it may be worthwile to revisit grounding abstractions in experience using those approaches.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This Tweet is unavailable.
-
In what ways are purely mathematical models of AI architectures insufficient for efficiently explaining the relationship between intermediate fine scale effects of model parametrization and terminal states?
End of conversation
-
-
-
“Contextual” category theory maybe? It seems we treat everything in this Franken-equilibrium states approach when the real problem is we don’t have a way to produce a satisfying taxonomy of /bf{dynamical} classes. They have to exists in certain limited contexts. I can feel em
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Something between category theory and information theory perhaps.
-
Biggest questions for me are finding/defining types and functors in differentiable programming. They probably need to be fuzzier than what category theorists are used to.
- Show replies
New conversation -
-
-
Perhaps renormalization group applied to understanding which approximate summary statistics will still have divergent terms when used to approximate stuff infinitely far away from the actual distributions they summarize, and how to systematically suppress those divergences.
-
This seems too specific to cover all of abstraction.
- Show replies
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.