Probabilistic Gate Selection

Each gate maintains a 16-dimensional probability distribution over binary operations, updated via gradient descent

Neighborhood — ranked by edge-count

framework

Deep Differentiable Logic Gate Networks
implements
Framework by Petersen et al. using logic gates as neurons with differentiable training, integrated into DiffLogic CA

concept

16 Possible Binary Operations
associated_with
The complete set of possible operations for a two-input binary gate over which DLGN learns a distribution
Pass-Through Gate Bias
associated_with
Initial gate distribution biased toward pass-through gates A and B to facilitate training stability

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.

gatesconcept0.762
Bayesian Model Selectionconcept0.759
Choosing among candidate models based on model evidence.
Probabilistic Bisection Algorithmmethod0.758
Algorithm used to calibrate per-latent threshold boost values for consistent first-attempt difficulty
probabilityconcept0.731
Measure of expected sensory input, core to linking value and surprise.
Binary Logic Gatesconcept0.728
Fundamental discrete computation units used as neurons in DLGN and DiffLogic CA
Probabilistic Body Schemaconcept0.717
The paper frames the self-prior as a probabilistic body schema capturing visual–proprioceptive associations
Different tasks yield distinct distributions of logic gate types between perception kernels and update networksclaim0.714
Interpretive claim based on circuit analysis across experiments
Logic Gate Perception Kernelsmethod0.713
Named technique in DiffLogic CA where fixed-structure logic circuits replace Sobel filters for neighborhood perception