Self-organized Boolean Computation via Neural Cellular Automata
zzznah · x · 2026-08-18
A project demonstrating self-organized boolean computation using Neural Cellular Automata (NCA).
Core Mechanics:
- A 16-channel cellular automaton where every cell runs the same learned rule.
- Trained via gradient descent without manual rule definition.
- Supervision applies only to the final grid state, leaving internal states unconstrained.
Demonstration:
- Input bits are drawn as circles on the left edge (bright for 1, dark for 0), and the answer emerges autonomously on the right edge.
- Capable of performing Boolean logic and binary addition.
- Despite each cell only sensing local neighbors, they collaborate to transport information and execute computations globally.
More from Research
- Scaling ML Infra for Million-Hour Robot Training — JasonMa2020 · 2026-08-18
- Stop Indexing at Full Precision: Compressed Vectors Cut Storage by 60x — _reachsumit · 2026-08-18
- RSI Bench Launches to Quantify Recursive Self-Improvement in AI — dhruv2038 · 2026-08-18
- Scale AI launches RSI-Bench: $2,000 per accepted task plus co-authorship for contributors — dhruv2038 · 2026-08-18
- Meta's Dear Algo: Agentic Intent Layer for Unified Search — _reachsumit · 2026-08-18
- Trident: Multi-Aspect Page Annotation for Long-Document VQA — _reachsumit · 2026-08-18