concept
active
concept:continuous-relaxation-of-logic-operationsContinuous Relaxation of Logic Operations
Key technique enabling gradient-based training of discrete logic gates by replacing binary operations with differentiable approximations
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- Deep Differentiable Logic Gate NetworksimplementsFramework by Petersen et al. using logic gates as neurons with differentiable training, integrated into DiffLogic CA
Methods (1)
method
- Gradient DescentusesUsed for updating hidden state expectations; provides dynamical process theory testable against neuronal data
Concepts (1)
concept
- Soft Lossassociated_withLoss computed using continuous relaxations of logic gates during training
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Framework borrowed from human metacognition research: when probe and self-report agree, confidence in both increases as they partially track the same underlying state
- A parallel programming approach using guarded clauses and shared logical variables, exemplified by Parlog and Concurrent Prolog.
- The key novel property of DiffLogic CA — logic gate networks that are recurrent both spatially and temporally
- Language model reasoning tasks with cyclic geometric structure used to test manifold steering.
- Brains perform simultaneous discrete operations (spikes) and continuous operations (graded potentials, fields) that co-determine each other; distinguishes biological from digital substrates.
- The novel framework introduced in this paper, combining DLGN and NCA for fully differentiable discrete CA learning
- A resource-sensitive combinatory algebra with modalities for copying; provides a fine-grained model of computation.
- Criticism of temporal logic as a verification tool.