Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2025 May 19;25(10):3191.
doi: 10.3390/s25103191.

Tiny Machine Learning and On-Device Inference: A Survey of Applications, Challenges, and Future Directions

Soroush Heydari  1 , Qusay H Mahmoud  1
Affiliations
Review

Tiny Machine Learning and On-Device Inference: A Survey of Applications, Challenges, and Future Directions

Soroush Heydari et al. Sensors (Basel). .

Abstract

The growth in artificial intelligence and its applications has led to increased data processing and inference requirements. Traditional cloud-based inference solutions are often used but may prove inadequate for applications requiring near-instantaneous response times. This review examines Tiny Machine Learning, also known as TinyML, as an alternative to cloud-based inference. The review focuses on applications where transmission delays make traditional Internet of Things (IoT) approaches impractical, thus necessitating a solution that uses TinyML and on-device inference. This study, which follows the PRISMA guidelines, covers TinyML's use cases for real-world applications by analyzing experimental studies and synthesizing current research on the characteristics of TinyML experiments, such as machine learning techniques and the hardware used for experiments. This review identifies existing gaps in research as well as the means to address these gaps. The review findings suggest that TinyML has a strong record of real-world usability and offers advantages over cloud-based inference, particularly in environments with bandwidth constraints and use cases that require rapid response times. This review discusses the implications of TinyML's experimental performance for future research on TinyML applications.

Keywords: IoT; TinyML; edge AI; edge computing; embedded ML; embedded systems; resource-constrained devices; sensors.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
TinyML hardware schema from [1].
Figure 2
Figure 2
PRISMA selection flowchart.
See this image and copyright information in PMC

References

    1. Abadade Y., Temouden A., Bamoumen H., Benamar N., Chtouki Y., Hafid A.S. A Comprehensive Survey on TinyML. IEEE Access. 2023;11:96892–96922. doi: 10.1109/ACCESS.2023.3294111. - DOI
    1. Capogrosso L., Cunico F., Cheng D.S., Fummi F., Cristani M. A Machine Learning-Oriented Survey on Tiny Machine Learning. IEEE Access. 2024;12:23406–23426. doi: 10.1109/ACCESS.2024.3365349. - DOI
    1. Elhanashi A., Dini P., Saponara S., Zheng Q. Advancements in TinyML: Applications, Limitations, and Impact on IoT Devices. Electronics. 2024;13:3562. doi: 10.3390/electronics13173562. - DOI
    1. Tsoukas V., Gkogkidis A., Boumpa E., Kakarountas A. A Review on the emerging technology of TinyML. ACM Comput. Surv. 2024;56:259. doi: 10.1145/3661820. - DOI
    1. Liu S., Wen D., Li D., Chen Q., Zhu G., Shi Y. Energy-Efficient Optimal Mode Selection for Edge AI Inference via Integrated Sensing-Communication-Computation. IEEE Trans. Mob. Comput. 2024;23:14248–14262. doi: 10.1109/TMC.2024.3440581. - DOI

LinkOut - more resources