framework
active
framework:neural-cellular-automataNeural Cellular Automata
Prior framework combining cellular automata with deep learning, extended by this work
Neighborhood — ranked by edge-count
Papers (1)
paper
- cimcWhitepapermentions
Methods (1)
method
- Gradient DescentimplementsUsed for updating hidden state expectations; provides dynamical process theory testable against neuronal data
Concepts (3)
concept
- MorphogenesisstudiesProcess by which cellular collectives generate large-scale structure and form; presented as a collective intelligence problem.
- Self-OrganizationimplementsSpontaneous emergence of long-range order in networks; modeled as neural and basal cognition.
- Cellular AutomataextendsFoundational computational paradigm of local rules producing emergent global behavior, extended by this work
Claims (1)
claim
- Authors' critique of NCA motivating the DiffLogic CA approach
Frameworks (2)
framework
- Growing Neural Cellular Automataextendsrelated_toSpecific NCA framework by Mordvintsev et al. for morphogenesis, whose conventions are adopted in this paper
- The novel framework introduced in this paper, combining DLGN and NCA for fully differentiable discrete CA learning
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.
- The model's parameters considered as the actual 'code' implementing its algorithms, as opposed to human-written code.
- Michael Johnson's prior work on how neural networks (and brains) can be 'annealed' to find optimal states.
- Brain-based physical implementations of consciousness-related functions, assumed by many ToCs to be exclusive.
- The artificial agents trained with RL in this study, whose latent dynamics are analyzed for causal emergence.
- Authors' broader vision claim linking their system to Toffoli and Margolus's programmable matter concept