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.

The first edition of the tinyML Challenge (in 2022) is organized by ITU in conjunction with the tinyML Foundation to to create a low-cost, low-power, reliable, accurate, easy to install and maintain weather station, with no mechanical moving parts for measuring all weather conditions with a focus on rain and wind, based on tinyML, that can be deployed locally.

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.

The first edition of the tinyML Challenge (in 2022) is organized by ITU in conjunction with the tinyML Foundation to to create a low-cost, low-power, reliable, accurate, easy to install and maintain weather station, with no mechanical moving parts for measuring all weather conditions with a focus on rain and wind, based on tinyML, that can be deployed locally.

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

Monday July 25, 2022

Monday August 15, 2022

Monday September 5, 2022

Monday October 3, 2022

Monday November 14, 2022

Proposal submission

Dataset checkpoint

Model checkpoint

Device checkpoint 

Final submission

tinyML Challenge Timeline

Monday July 25, 2022 

Proposal submission

Monday August 15, 2022

Dataset checkpoint

Monday September 5, 2022

Model checkpoint

Monday October 3, 2022 

Device checkpoint 

Monday November 14, 2022 

Final submission

Related sessions
1 June 2022
16:30 - 17:40 CEST, Geneva | 10:30-11:40 EDT, New York | 22:30-23:40 CST, Beijing
Michele Polese (Northeastern University), Thomas Basikolo (ITU), Vishnu Ram OV
13 June 2022
18:00 - 19:30 CEST, Geneva | 12:00-13:30 EST, New York | 00:00-01:30 CST, Beijing
Thomas Basikolo (ITU), Vishnu Ram OV, Ahmed Alkhateeb (Arizona State University)
15 June 2022
15:00 - 16:30 CEST Geneva | 21:00-22:30 CST, Beijing | 09:00-10:30 EST, New York
Jelena Senic (NIST), Raied Caromi (National Institute of Standards and Technology, CTL, Wireless and Network Division), Steve Blandino (NIST)
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)

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​