Recurrent Logic Circuit

The key novel property of DiffLogic CA — logic gate networks that are recurrent both spatially and temporally

Neighborhood — ranked by edge-count

framework

Differentiable Logic Cellular Automata (DiffLogic CA)
implements
The novel framework introduced in this paper, combining DLGN and NCA for fully differentiable discrete CA learning

concept

Binary Cell State
associated_with
Core feature distinguishing DiffLogic CA from NCA — each cell's state is fully binary rather than continuous

cosine ≥ 0.65 · no typed edge

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

Recurrent networksconcept0.776
Networks with loop connections that can maintain internal state and exhibit dynamical attractors.
Recurrent Integrationconcept0.762
Computational property emphasized across consciousness theories as necessary for conscious processing
Algorithmic recurrenceconcept0.751
Processing where the same operation is applied repeatedly via weight sharing, as in RNNs; contrasts with implementational recurrence.
Implementational recurrenceconcept0.748
Recurrence via feedback loops where individual neurons process information repeatedly.
Recurrent Position Encodingsmethod0.747
Key modification to transformers proposed in this paper: position encodings generated by a recurrent network trained on action sequences.
Circuits Threadframework0.743
An open scientific collaboration hosted on Distill slack studying the inner workings of neural networks via zoomed-in mechanistic investigation
Differentiable Logic Gate Networks have not previously been shown to work in recurrent settings prior to this workclaim0.743
Authors' novelty assertion establishing the gap filled by DiffLogic CA
Sparse circuitsconcept0.742
A goal in mechanistic interpretability to identify sparse computational subgraphs; VPD promotes sparse parameter circuits.