# A Sensitivity Analysis of Cellular Automata and Heterogeneous Topology Networks: Partially-Local Cellular Automata and Homogeneous Homogeneous Random Boolean Networks

arXiv: https://arxiv.org/abs/2407.18017 · HTML: https://mlsanity.com/paper/2407.18017/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 105 references that are in the map.
- First posted on arXiv 25 Jul 2024.

## Builds on (most cited first, 11 of 11)

- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Power Hungry Processing: Watts Driving the Cost of AI Deployment?](https://mlsanity.com/paper/2311.16863/) (2023)
- [Echo state networks are universal](https://mlsanity.com/paper/1806.00797/) (2018)
- [Lenia - Biology of Artificial Life](https://mlsanity.com/paper/1812.05433/) (2018)
- [Learning Graph Cellular Automata](https://mlsanity.com/paper/2110.14237/) (2021)
- [Reservoir Computing using Cellular Automata](https://mlsanity.com/paper/1410.0162/) (2014)
- [Reservoir Computing Using Non-Uniform Binary Cellular Automata](https://mlsanity.com/paper/1702.03812/) (2017)
- [Reservoir Computing and Extreme Learning Machines using Pairs of Cellular Automata Rules](https://mlsanity.com/paper/1703.05807/) (2017)
- [Computational Hierarchy of Elementary Cellular Automata](https://mlsanity.com/paper/2108.00415/) (2021)
- [ReLiCADA -- Reservoir Computing using Linear Cellular Automata Design Algorithm](https://mlsanity.com/paper/2308.11522/) (2023)
- [On when is Reservoir Computing with Cellular Automata Beneficial?](https://mlsanity.com/paper/2407.09501/) (2024)

## Abstract (arXiv)

Elementary Cellular Automata (ECA) are a well-studied computational universe that is, despite its simple configurations, capable of impressive computational variety. Harvesting this computation in a useful way has historically shown itself to be difficult, but if combined with reservoir computing (RC), this becomes much more feasible. Furthermore, RC and ECA enable energy-efficient AI, making the combination a promising concept for Edge AI. In this work, we contrast ECA to substrates of Partially-Local CA (PLCA) and Homogeneous Homogeneous Random Boolean Networks (HHRBN). They are, in comparison, the topological heterogeneous counterparts of ECA. This represents a step from ECA towards more biological-plausible substrates. We analyse these substrates by testing on an RC benchmark (5-bit memory), using Temporal Derrida plots to estimate the sensitivity and assess the defect collapse rate. We find that, counterintuitively, disordered topology does not necessarily mean disordered computation. There are countering computational "forces" of topology imperfections leading to a higher collapse rate (order) and yet, if accounted for, an increased sensitivity to the initial condition. These observations together suggest a shrinking critical range.