Can a Differentiable Logic CA learn at all?

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Differentiable Logic Cellular Automata (DiffLogic CA)framework0.784
  The novel framework introduced in this paper, combining DLGN and NCA for fully differentiable discrete CA learning
• DiffLogic CA can directly learn the local rules needed to achieve desired macroscopic computation, addressing the fundamental challenge identified by Toffoli and Margolusclaim0.733
  Core thesis of the paper framed against the historical challenge of hand-crafting CA rules
• Synchronously trained DiffLogic CA circuit succeeds at asynchronous inference without retrainingfinding0.724
  Unexpected result demonstrating robustness of learned circuits beyond their training regime
• DiffLogic CA represents, to best of authors' knowledge, the first exploration of differentiable logic gate networks in a recurrent settingfinding0.719
  Novelty claim about the contribution to the field
• Learned simulations can be partially observed and lazily-rendered, and still work.claim0.717
  One of the updates about prosaic ML simulation.
• Differentiable Logic Gate Networks have not previously been shown to work in recurrent settings prior to this workclaim0.707
  Authors' novelty assertion establishing the gap filled by DiffLogic CA
• DiffLogic CA learned fault tolerance and self-healing behavior without explicit design for these conditionsfinding0.706
  Key finding on robustness — both permanent and temporary cell deactivation handled gracefully
• Friston, FitzGerald et al. (2016) — Active inference and learningconcept0.704
  Prior active inference paper providing detailed neurophysiological implementation of belief updates