clearly you can process information by modelling a physical system, or you can model artificial systems as graph reductions, or you can produce infinite loops of arithmetic operators to obscure input is there a fourth one?
if you're feeding your inputs into a complex artificial nonlinear system model, that might be a fourth; like, maybe it can be constructed as graph reduction in some sense but hardly usefully
-
-
this is giving minksy too much credit, most nonlinearities introduced into systems of that sort can be simply expressed as dynamical relations, that's the really interesting part of like differentiable programming, lots of physical analysis directly applicable
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.