tinyML Challenge

The Future of ML is Tiny and Bright– applying machine learning to edge devices

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.

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.

Challenge Prizes

1st place prize: $3,000

2nd place prize: $2,000

3rd place prize: $1,000

Additional prizes to be announced.

Cash prizes paid in cash or equivalent (gift card); amounts in US dollars. All awards are made in compliance with international monetary transfer restrictions and reporting requirements. Void where prohibited by law.

tinyML Challenge Timeline

25 August 2023

22 September 2023

10 November 2023

December 2023 

Proposal submission

Model checkpoint

Final submission

Awards

tinyML Challenge Timeline

25 August 2023

Proposal submission

22 September 2023

Model checkpoint

10 November 2023

Final submission

December 2023 

Awards

Problem statements

Smart Weather Station

Create cost-effective, low-power, reliable, accurate, easy to install and maintain, and free of mechanical moving parts weather station

Plant Disease Detection

create scalable and high-performance tinyML solutions utilizing open datasets, specifically focusing on plant disease detection

Wildlife Monitoring

create scalable and high-performance tinyML solutions utilizing open datasets focusing on wildlife monitoring

Related sessions
21 July 2022
16:00 - 17:15 CEST, Geneva | 07:00-08:15 PDT, California | 10:00-11:15 EST, New York | 22:00-23:15 CST, Beijing
Marco Zennaro (Abdus Salam International Centre for Theoretical Physics), Thomas Basikolo (ITU), Alessandro Grande (Edge Impulse)
25 August 2023
14:00 - 15:00 CEST Geneva | 08:00-09:00 EDT, New York | 20:00-21:00 CST, Beijing
Marco Zennaro (Abdus Salam International Centre for Theoretical Physics), Thomas Basikolo (ITU), Jona Beysens (CSEM)
27 November 2023
14:00 - 15:30 CET Geneva | 08:00-09:30 EST, New York | 21:00-22:30 CST, Beijing
Jona Beysens (CSEM), Marco Zennaro (Abdus Salam International Centre for Theoretical Physics), Thomas Basikolo (ITU)...

Organizers

The Challenge is co-organized by ITU and tinyML Foundation

HighRes_RGB_ITUlogo_009CD6
TinyML-512px

Partners

TinyML-512px
ictp_head_logo
EdgeImpulse-500px

Sponsorship Inquiries​