Emergent ComputingResearch
Emergent and evolutionary computation
How small rules, search and selection produce programs that generalise. Pinned posts describe our lines of work and are kept up to date; posts below are dated notes, hypotheses and results, newest first.
Pinned
Emergent Models
Framework, latent-universality theorem, and experiments on discrete and continuous substrates: EM43, Game of Life, CEM1D, CEM2D.
In progressLatent-universal machines
LUTM-1, LUTM-6 and LU-A: small machines whose rule and interface never change. Only the program differs between tasks, and we measure how hard programs are to find.
In progressNCPU-EM
Neural cellular automata with one shared rule and a learned program per task. Builds on NCPU by Zhechev and Walas.
Posts
- Iteration and reasoning: looped transformers, ACT and Emergent Models
What looped and adaptive-time models have in common with Emergent Models, and four hypotheses we want to test.
- Local rules on parallel hardware
Search on GPUs, cellular arithmetic, and the limit that locality puts on latency.
- What the Emergent Models paper shows, and what it does not
The claims, the evidence behind each, and the open problems.
- Applied research
Joint projects where small iterated models, program search or evolutionary optimisation fit the problem.