Reference library
Growing Neural Cellular Automata
Paper summary
Trains shared local neural cellular-automaton rules to grow target patterns from seeds. Persistence and damage training produce stronger long-term stability and regeneration, illustrating learned distributed morphogenesis.
Relevance to the project
A reference for regular GPU execution and controlled damage-recovery tests. Its target-image loss, grid, and alive mechanism must be counted as predefined substrate and training choices.
Regeneration under external training is not proof of spontaneous self-maintenance.
Source record
- Reference ID
- article-https-distill-pub-2020-growing-ca
- Archived version
- Cited online article
- Summary provenance
- reference-library/papers/article-https-distill-pub-2020-growing-ca/metadata.json · summary
- Review status
- initial orientation summary; not a critical full-paper review
- Reading scope
- Selected abstract/opening and available closing discussion/conclusion passages in the preserved text extract; broader project notes provide context. No reproduction of experiments, exhaustive methods review, or equation/figure audit.