# On when is Reservoir Computing with Cellular Automata Beneficial?

arXiv: https://arxiv.org/abs/2407.09501 · HTML: https://mlsanity.com/paper/2407.09501/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 38 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Builds on (most cited first, 9 of 9)

- [The UCR Time Series Archive](https://mlsanity.com/paper/1810.07758/) (2018)
- [No Routing Needed Between Capsules](https://mlsanity.com/paper/2001.09136/) (2020)
- [Reservoir Computing using Cellular Automata](https://mlsanity.com/paper/1410.0162/) (2014)
- [Binary Embedding: Fundamental Limits and Fast Algorithm](https://mlsanity.com/paper/1502.05746/) (2015)
- [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)
- [Reservoir Computing Hardware with Cellular Automata](https://mlsanity.com/paper/1806.04932/) (2018)
- [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)

## Built on by (most cited first, 1 of 1)

- [A Sensitivity Analysis of Cellular Automata and Heterogeneous Topology Networks: Partially-Local Cellular Automata and Homogeneous Homogeneous Random Boolean Networks](https://mlsanity.com/paper/2407.18017/) (2024)

## Abstract (arXiv)

Reservoir Computing with Cellular Automata (ReCA) is a relatively novel and promising approach. It consists of 3 steps: an encoding scheme to inject the problem into the CA, the CA iterations step itself and a simple classifying step, typically a linear classifier. This paper demonstrates that the ReCA concept is effective even in arguably the simplest implementation of a ReCA system. However, we also report a failed attempt on the UCR Time Series Classification Archive where ReCA seems to work, but only because of the encoding scheme itself, not in any part due to the CA. This highlights the need for ablation testing, i.e., comparing internally with sub-parts of one model, but also raises an open question on what kind of tasks ReCA is best suited for.