TinyML
TinyML (short for tiny machine learning) is an area of machine learning that focuses on deploying and running models on low-power, resource-constrained embedded systems such as microcontrollers and edge devices.[1][2][3][4]
TinyML supports on-device inference with low latency and minimal reliance on cloud connectivity, which makes it suitable for applications in the Internet of Things (IoT), wearable devices, and real-time systems.[5]
History
[edit]The idea of running machine learning models on embedded systems has gained traction in the late 2010s, as model compression, quantization, and efficient neural network architectures progressed.[6]
The term TinyML was popularized in 2019 with the publication of the book TinyML by Pete Warden and Daniel Situnayake and the creation of the TinyML Foundation.[1]
See also
[edit]Further reading
[edit]Warden, Pete; Situnayake, Daniel (2020). TinyML: machine learning with TensorFlow Lite on Arduino and ultra-low-power microcontrollers (1st ed.). Bejing Boston Farnham Sebastopol Tokyo: O'Reilly. ISBN 978-1-4920-5204-3.
References
[edit]- ^ a b Warden, Pete; Situnayake, Daniel (2019). TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers. O'Reilly Media..
- ^ "What is TinyML? Tiny Machine Learning". GeeksforGeeks. 4 January 2024. Retrieved 27 April 2026.
- ^ Prakash, Shvetank; Njor, Emil; Banbury, Colby; Stewart, Matthew; Janapa, Vijay (6 May 2024). "TinyML: Why the Future of Machine Learning is Tiny and Bright". SIGARCH. Retrieved 27 April 2026.
- ^ Han, Hui; Trimi, Silvana; Lee, Sang M. (1 March 2026). "Tiny Machine Learning (TinyML): Research trends and future application opportunities". Array. 29 100674. doi:10.1016/j.array.2025.100674. ISSN 2590-0056.
- ^ Davidson, Joe (2021). "Enabling TinyML for IoT Applications". IEEE Internet of Things Journal.
- ^ Gupta, Suyog; Agrawal, Ankur; Gopalakrishnan, Kailash; Narayanan, Pritish (2015). "Deep Learning with Limited Numerical Precision". Proceedings of the 32nd International Conference on Machine Learning. 37: 1737–1746. Retrieved 30 April 2026.