Turing universal neural networks do not require global clocks

3 min read Original article ↗

Nature Communications (2026) Cite this article

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”.

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Massachusetts, Amherst, MA, USA

    Hava T. Siegelmann & Chloé Becquey

  2. Department of Biological Engineering, Massachusetts Institute of Technology, Cambridge, MA, USA

    Roy N. Siegelmann

  3. Department of Engineering, Cambridge University, Cambridge, UK

    Stephen Chung

Authors

  1. Hava T. Siegelmann
  2. Roy N. Siegelmann
  3. Stephen Chung
  4. Chloé Becquey

Corresponding author

Correspondence to Hava T. Siegelmann.

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

About this article

Check for updates. Verify currency and authenticity via CrossMark

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

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1038/s41467-026-73830-6