TALK
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 will bridge the gap between traditional signal processing techniques and modern AI, demonstrating how established mathematical tools can inspire next-generation machine learning. We'll 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?
WISDOM CORNER: LIVE LIFE LESSONS
Participants will have the chance to hear from Prof. Pérez-Neira about his impactful life lessons over the years as well as his advice to young researchers in the field of information and communication technologies.
Register here
|
SPEAKER:
Ana Pérez-Neira, Universitat Politècnica de Catalunya, Spain
Ana Pérez-Neira is full professor at the Polytechnic University of Catalonia's (UPC) Signal Theory and Communication Department. From 2010 to 2014, she served as Vice Rector for Research at UPC. Currently, she leads as the Director of the CTTC – Centre Tecnològic de Telecomunicacions de Catalunya. As an IEEE and EURASIP Fellow and recipient of prestigious awards like the ICREA Academia and Narcís Monturiol distinctions, she dedicated her career to advancing multi-channel signal processing, optimisation, and satellite communications. Her role as the coordinator of the European Space Agency's Satellite Network of Experts (SatNEx) from 2015 to 2025 has been pivotal in building a leading community in this field. Her academic and professional journey is rooted in a deep passion for innovation and collaboration. With over 80 journal papers, 400 conference papers, 70 invited talks, and seven co-authored books, her work spans decades of impactful research. She has led over 30 projects, holds eight patents, and has chaired some of the largest international conferences in telecommunications, including ICASSP 2020, which became the first fully virtual conference due to COVID-19, with 15,000 attendees. She is elected member of the Royal Academy of Science and Arts of Barcelona and of the Royal Academy of Engineering of Spain.
|
|
MODERATOR: Ian F. Akyildiz, ITU J-FET Editor-in-Chief and Truva Inc., USA
|
