Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Research Briefing
  • Published:

Tiny classifier circuits as accelerators for classification of tabular data

A methodology — called auto tiny classifiers — is proposed to directly generate predictor circuits for the classification of tabular data, searching over the space of combinational logic using an evolutionary algorithm to maximize training prediction accuracy. Prediction performance is comparable to typical machine learning methods, but substantially fewer hardware resources and power are required.

This is a preview of subscription content, access via your institution

Access options

Buy this article

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Existing approaches to the generation of ML hardware as accelerators.

References

  1. Biggs, J. et al. A natively flexible 32-bit Arm microprocessor. Nature 595, 532–536 (2021). This paper introduced an Arm microprocessor fabricated using metal–oxide thin-film transistor technology on flexible substrates, which paved the way for the development of low-cost and non-silicon integrated systems.

    Article  Google Scholar 

  2. Ozer, E. et al. Bespoke machine learning processor development framework on flexible substrates. In 2019 IEEE International Conference on Flexible and Printable Sensors and Systems (FLEPS) 1–3 (IEEE, 2019). This paper proposes a framework for the fast design of ML processors on flexible substrates, with rapid development and fabrication cycles that are key for the design of processors for FMCG markets.

  3. Ozer, E. et al. A hardwired machine learning processing engine fabricated with submicron metal-oxide thin-film transistors on a flexible substrate. Nat. Electron. 3, 419–425 (2020). This paper presents a processing engine fabricated on flexible substrates for odour recognition using ML.

    Article  Google Scholar 

  4. Ozer, E. et al. Binary neural network as a flexible integrated circuit for odour classification. In 2020 IEEE International Conference on Flexible and Printable Sensors and Systems (FLEPS) 1–4 (IEEE, 2020). This paper sets out the development of binary neural networks on flexible substrates for odour classification.

  5. Ozer, E. et al. Malodour classification with low-cost flexible electronics. Nat. Commun. 14, 777 (2023). This paper reports a decision-tree-based ML model that is trained to assess the strength of human odour.

    Article  Google Scholar 

Download references

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This is a summary of: Iordanou, K. et al. Low-cost and efficient prediction hardware for tabular data using tiny classifier circuits. Nat. Electron. https://doi.org/10.1038/s41928-024-01157-5 (2024).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tiny classifier circuits as accelerators for classification of tabular data. Nat Electron 7, 334–335 (2024). https://doi.org/10.1038/s41928-024-01166-4

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41928-024-01166-4

Search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing