Tiny Machine Learning and On-Device Inference: A Survey of Applications, Challenges, and Future Directions
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 Mach...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/10/3191 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850256389573705728 |
|---|---|
| author | Soroush Heydari Qusay H. Mahmoud |
| author_facet | Soroush Heydari Qusay H. Mahmoud |
| author_sort | Soroush Heydari |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-a8a92f78b9d04ca08daffa2cef92e59e |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-a8a92f78b9d04ca08daffa2cef92e59e2025-08-20T01:56:39ZengMDPI AGSensors1424-82202025-05-012510319110.3390/s25103191Tiny Machine Learning and On-Device Inference: A Survey of Applications, Challenges, and Future DirectionsSoroush Heydari0Qusay H. Mahmoud1Department of Electrical, Computer and Software Engineering, Ontario Tech University, Oshawa, ON L1G 0C5, CanadaDepartment of Electrical, Computer and Software Engineering, Ontario Tech University, Oshawa, ON L1G 0C5, CanadaThe 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.https://www.mdpi.com/1424-8220/25/10/3191TinyMLIoTsensorsedge AIedge computingembedded ML |
| spellingShingle | Soroush Heydari Qusay H. Mahmoud Tiny Machine Learning and On-Device Inference: A Survey of Applications, Challenges, and Future Directions Sensors TinyML IoT sensors edge AI edge computing embedded ML |
| title | Tiny Machine Learning and On-Device Inference: A Survey of Applications, Challenges, and Future Directions |
| title_full | Tiny Machine Learning and On-Device Inference: A Survey of Applications, Challenges, and Future Directions |
| title_fullStr | Tiny Machine Learning and On-Device Inference: A Survey of Applications, Challenges, and Future Directions |
| title_full_unstemmed | Tiny Machine Learning and On-Device Inference: A Survey of Applications, Challenges, and Future Directions |
| title_short | Tiny Machine Learning and On-Device Inference: A Survey of Applications, Challenges, and Future Directions |
| title_sort | tiny machine learning and on device inference a survey of applications challenges and future directions |
| topic | TinyML IoT sensors edge AI edge computing embedded ML |
| url | https://www.mdpi.com/1424-8220/25/10/3191 |
| work_keys_str_mv | AT soroushheydari tinymachinelearningandondeviceinferenceasurveyofapplicationschallengesandfuturedirections AT qusayhmahmoud tinymachinelearningandondeviceinferenceasurveyofapplicationschallengesandfuturedirections |