SPS Webinar: Signal Processing for Expressive Neural Networks: Toward Lightweight Intelligence
Date: 05-November-2025
Time: 10:30 AM ET (New York Time)
Presenter: Dr. Ana Perez-Neira
Abstract
AI keeps getting bigger—but does bigger always mean better? As Large Language Models (LLMs) take center stage, their enormous resource demands raise pressing concerns about sustainability and efficiency. In this webinar, the presenter questioned the assumption that AI must be massive to be powerful.
They introduced the Expressive Neural Network (ENN), a novel architecture that reimagines activation functions through the lens of classical signal processing—specifically, the Discrete Cosine Transform (DCT). This innovative design boosts a network’s flexibility and expressiveness, enabling faster convergence and much smaller models that cut both energy use and computational costs.
Their discussion bridged traditional signal processing and modern AI, showing how established mathematical tools can inspire the next generation nonlinear signal processing. They explored how ENNs could transform edge computing by bringing efficient AI to resource-constrained environments, and why expressiveness—not mere size—holds the key to the future of neural networks.
If LLMs represent the brute force of AI, ENNs may become a precision instrument. Looking ahead, they anticipate the rise of new model types—such as Small Language Models and specialized architectures—opening the door to more sustainable, purpose-driven AI deployment.
Biography
Ana Pérez-Neira (SM’02, FM’20) received the Telecommunication Engineering degree in 1991 from the Universitat Politècnica de Catalunya (UPC) and the PhD degree in 1995 from the same university. Her major fields of study are array processing and signal processing for communications.
She is currently a full professor at UPC in the Signal Theory and Communication Department since 2006. From 2010 to 2014, she served as Vice Rector for Research at UPC. Currently, she is the Director of the research center CTTC – Centre Tecnològic de Telecomunicacions de Catalunya. Her current research interests are satellite communications and nonlinear signal processing. 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.
Prof. Pérez-Neira is an IEEE and EURASIP Fellow and recipient of prestigious awards like the ICREA Academia and Narcís Monturiol distinctions. She is elected member of the Royal Academy of Science and Arts of Barcelona and of the Royal Academy of Engineering of Spain. She has been IEEE SPS VP Conferences and General Chair of ICASSP20 and ICASSP26.
