Differentiable Logic Gate Networks have not previously been shown to work in recurrent settings prior to this work

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

• Deep Differentiable Logic Gate Networksframework0.801
  Framework by Petersen et al. using logic gates as neurons with differentiable training, integrated into DiffLogic CA
• Different tasks yield distinct distributions of logic gate types between perception kernels and update networksclaim0.774
  Interpretive claim based on circuit analysis across experiments
• Recurrent Logic Circuitconcept0.743
  The key novel property of DiffLogic CA — logic gate networks that are recurrent both spatially and temporally
• The integration of differentiable logic gates and neural cellular automata is a potential step towards programmable matter — Computroniumclaim0.729
  Authors' broader vision claim linking their system to Toffoli and Margolus's programmable matter concept
• Can recurrent-in-space and recurrent-in-time circuits learn complex patterns similar to those generated by traditional NCAs?question0.710
  Second and more profound research question motivating the pattern generation experiment
• Can a Differentiable Logic CA learn at all?question0.707
  First fundamental question motivating the Game of Life experiment
• Deep representations have a special significance in recurrent networks, allowing coordinated behaviour without losing sensitivity to new inputs.claim0.704
  Importance of hierarchical structure for flexible coordination.
• Early layers of convolutional networks are more interchangeable than later layers across different architecturesfinding0.695
  Lenc & Vedaldi finding on layer-wise alignment