Page 13 - Crowdsourcing AI and Machine Learning solutions for SDGs - ITU AI/ML Challenges 2024 Report

Crowdsourcing AI and Machine Learning solutions for SDGs

3 Domains and Areas of Competition

Since 2020, the ITU AI/ML Challenge has evolved to include multiple domains, each addressing
specific areas of interest and impact. These competitions are run annually, with each edition
introducing new themes and expanding the scope of the challenge. The competitions have
included AI/ML in 5G and 6G (i.e. communication networks), GeoAI, tinyML, AI for Climate
Action, and Fusion. Each domain offers unique opportunities for participants to apply their
skills, gain hands-on experience, and contribute to solving pressing global issues.

3.1 AI/ML in 5G and 6G (Communication Networks)

Applying machine learning in
communication networks
The ITU AI/ML in 5G Challenge rallies
like-minded students and professionals
from around the globe to solve real-world
problems in communication networks by
applying AI and machine learning (ML).
The AI/ML in 5G Challenge, launched as
the first edition in 2020, has become a
cornerstone of the ITU AI/ML Challenge.
This competition focuses on applying
AI/ML in communication networks,
particularly in the development and
optimization of 5G and emerging 6G
technologies. As telecommunication
networks evolve towards 6G, AI is expected
to be integral to the network’s design,
enabling advanced features like AI-native
infrastructure, pervasive intelligence, and
real-time responsiveness.

ITU AI/ML in 5G Challenge analyses practical problems in networks using real and simulated
data. As we aim for enhanced efficiency, reliability, and rich user experience using AI/ML in
communication networks, ITU calls for the application of its pre-standard and standard concepts
in network management, security, optimization, and beyond to solve real-world problems. In
the ITU AI/ML in 5G Challenge, participants from various backgrounds collaborate to solve
real-world problems using AI/ML, working on curated problem statements with access to a
mix of real-world and simulated data. The challenge includes technical webinars, mentoring,
and hands-on sessions, enabling participants to create, train, and deploy ML models for
communication networks. The competition not only showcases talent and innovative solutions
but also provides a pathway for participants to engage with ITU standards and gain global
recognition.

5