- Article
- Open access
- Published:
Nature Communications (2026) Cite this article
-
2964 Accesses
-
40 Altmetric
We are providing an unedited version of this manuscript to give early access to its findings. Before final publication, the manuscript will undergo further editing. Please note there may be errors present which affect the content, and all legal disclaimers apply.
Subjects
Abstract
Recurrent neural networks were proven to be Turing universal in the 1990s, motivating computational complexity studies of spiking networks, neural Turing machines with differentiable activations, and transformers. At the time, neural networks were exploratory and small, whereas today large-scale deployment makes energy efficiency critical. We thus extend the development of computational foundations of neural networks to asynchronous networks. Asynchrony is modeled by updating a single randomly selected neuron per step, eliminating global updates and reducing energy use. While asynchrony introduces variability in update sequences and thus has often been considered impractical for computing, we introduce design constraints which lead to Turing universal asynchronous architectures. We prove universality both for asynchronous fixed architectures with varying-precision neurons and for variable architectures with fixed-precision neurons. These results advance the theoretical understanding of asynchronous networks, suggesting that they preserve full computational power, remain amenable for efficient training, and may achieve substantial reductions in energy use.
Similar content being viewed by others
Acknowledgements
We thank Eric Goldstein for providing editing and language clarification. H.S. discloses support for the research of this work from the National Science Foundation under Award No. 2231463 ("EAGER: Neural Networks that Temporally Change (NOTCH)”) and from the Air Force Office of Scientific Research through Acceptance Letter 24IOE006 for the project “Cooperative Multi-Agent Lifelong Learners for Scalable AI”.
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Siegelmann, H.T., Siegelmann, R.N., Chung, S. et al. Turing universal neural networks do not require global clocks. Nat Commun (2026). https://doi.org/10.1038/s41467-026-73830-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41467-026-73830-6