# Reservoir Computing using Cellular Automata

arXiv: https://arxiv.org/abs/1410.0162 · HTML: https://mlsanity.com/paper/1410.0162/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2014.

## Built on by (most cited first, 8 of 8)

- [A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning](https://mlsanity.com/paper/2307.15092/) (2023)
- [ReservoirComputing.jl: An Efficient and Modular Library for Reservoir Computing Models](https://mlsanity.com/paper/2204.05117/) (2022)
- [ReLiCADA -- Reservoir Computing using Linear Cellular Automata Design Algorithm](https://mlsanity.com/paper/2308.11522/) (2023)
- [Benchmarking Learning Efficiency in Deep Reservoir Computing](https://mlsanity.com/paper/2210.02549/) (2022)
- [On when is Reservoir Computing with Cellular Automata Beneficial?](https://mlsanity.com/paper/2407.09501/) (2024)
- [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)
- [MOGNET: A Mux-residual quantized Network leveraging Online-Generated weights](https://mlsanity.com/paper/2501.09531/) (2025)
- [Emergent Models: Intelligence from Tiny Substrates](https://mlsanity.com/paper/2608.14019/) (2026)

## Abstract (arXiv)

We introduce a novel framework of reservoir computing. Cellular automaton is used as the reservoir of dynamical systems. Input is randomly projected onto the initial conditions of automaton cells and nonlinear computation is performed on the input via application of a rule in the automaton for a period of time. The evolution of the automaton creates a space-time volume of the automaton state space, and it is used as the reservoir. The proposed framework is capable of long short-term memory and it requires orders of magnitude less computation compared to Echo State Networks. Also, for additive cellular automaton rules, reservoir features can be combined using Boolean operations, which provides a direct way for concept building and symbolic processing, and it is much more efficient compared to state-of-the-art approaches.