Beyond black-box AI: Expressive neural networks for smarter, lighter intelligence

Channel:
Subscribers:
20,600
Published on ● Video Link: https://www.youtube.com/watch?v=1HIeSpYk74M



Duration: 0:00
207 views
9


AI is getting bigger, but does bigger always mean better? As Large Language Models (LLMs) dominate the scene, their staggering resource consumption raises urgent questions about sustainability and efficiency. In this webinar, we challenge the notion that AI must be massive to be powerful. We introduce the Expressive Neural Network (ENN), a novel architecture that rethinks activation functions through the lens of classical signal processing – specifically, the Discrete Cosine Transform (DCT). This innovative approach not only enhances a network’s flexibility and expressiveness but also leads to faster convergence and significantly smaller models, reducing both energy consumption and computational costs. ​

Our discussion bridges the gap between traditional signal processing techniques and modern AI, demonstrating how established mathematical tools can inspire next-generation machine learning. We explore how ENNs can revolutionize edge computing, enabling efficient AI in resource-constrained environments, and why expressiveness – not just size – is the key to the future of neural networks. If LLMs are the brute force of AI, could ENNs be its precision tool?

Speakers:
Ana Isabel Pérez-Neira
Director, Centre Tecnològic de Telecomunicacions de Catalunya, Spain

Moderators:
Ian F. Akyildiz
ITU J-FET Editor-in-Chief and Truva Inc., USA​​​
Wisdom corner

Moderators:
Alessia Magliarditi
ITU Journal Manager, International Telecommunication Union (ITU)

AI for Good is identifying innovative AI applications, building skills and standards, and advancing partnerships to solve global challenges.

AI for Good is organized by ITU in partnership with over 40 UN Sister Agencies and co-convened with the Government of Switzerland.

Join the Neural Network!
👉https://aiforgood.itu.int/neural-network/
The AI for Good networking community platform powered by AI.
Designed to help users build connections with innovators and experts, link innovative ideas with social impact opportunities, and bring the community together to advance the SDGs using AI.

🔴 Watch the latest #AIforGood videos!
https://www.youtube.com/c/AIforGood/videos

📩 Stay updated and join our weekly AI for Good newsletter:
http://eepurl.com/gI2kJ5

🗞Check out the latest AI for Good news:
https://aiforgood.itu.int/newsroom/

📱Explore the AI for Good blog:
https://aiforgood.itu.int/ai-for-good-blog/

🌎 Connect on our social media:
Website: https://aiforgood.itu.int/
X: https://twitter.com/AIforGood
LinkedIn Page: https://www.linkedin.com/company/26511907
LinkedIn Group: https://www.linkedin.com/groups/8567748
Instagram: https://www.instagram.com/aiforgood
Facebook: https://www.facebook.com/AIforGood

Disclaimer:
The views and opinions expressed are those of the panelists and do not reflect the official policy of the ITU.




Other Videos By AI for Good


2025-09-12AI for Climate Innovation Factory 2025 live pitching session – 1st session
2025-09-11Quantum World Tour: Malta
2025-09-11Challenging the status Quo of AI security
2025-09-10More than a Summit – Frederic Werner, Chief, Strategy and Operations (AI for Good)
2025-09-04Agents of change: A 7 year old’s lens on Generation AI for Good
2025-09-02MX-AI: Multi-x automation and intelligence ecosystem
2025-08-29Beyond best effort: Reliable and efficient AI for wireless systems
2025-08-26AI for Good Global Summit 2025 - Media Coverage
2025-08-26When ITU Meets Innovation: Dr. Bilel Jamoussi and Dr. Jian Wang on AI for Good
2025-08-25ITU AI/ML Challenge Finale – Radio Resource Management (RRM) for 6G in-X Subnetworks
2025-08-25Beyond black-box AI: Expressive neural networks for smarter, lighter intelligence
2025-08-22Brain-Computer interface: Key technical standards and diverse application scenarios
2025-08-22Bridging frontier innovation with non-profit practice
2025-08-22Global AI convergence: Innovative practices for a shared sustainable future
2025-08-22AI and sustainability walk into a café: Satellites, data centres in space and beyond
2025-08-22End data disparity: A global initiative to support tri-sector partnerships in data and AI
2025-08-22AI-generated content: Emerging practices for platforms and users
2025-08-22From principles to practice: How AI standards enable effective governance
2025-08-22Empowering equal access to healthcare with AI
2025-08-22Developing responsible AI: Vision and practice
2025-08-22AI policy bytes



Tags:
AI for Good
AI
Artificial Intelligence
Machine Learning
Deep Learning
AI for Good Global Summit
ITU Journal