tinyML is a cutting-edge field that brings the power of machine learning (ML) to the performance- and power-constrained domain of tiny devices and embedded systems. This is a fast growing field of ML technologies and applications including hardware, algorithms, and software capable of performing on-device sensor (vision, audio, IMU, biomedical, etc.) data analytics at extremely low power, enabling a variety of always-on use-cases.
ITU, along with industry partners, is organizing the second edition of the tinyML Challenge in 2023. The objective is to develop a Next-Gen tinyML Smart Weather Station that is cost-effective, low-power, reliable, accurate, easy to install and maintain, and free of mechanical moving parts. This weather station will be designed to measure various weather conditions, particularly rain and wind, using tinyML technology, and it can be easily deployed locally.
Additionally, the tinyML Challenge seeks to explore Scalable and High-Performance tinyML solutions for crop disease detection and wildlife monitoring.