LECTURE SERIES “ROBUST AI”: MANUEL ROVERI

The next lecture in out lecture series will be given by Prof. Manuel Roveri (Politecnico di Milano) on the topic of Tiny Machine Learning: From Algorithms to Technology (And Back)”. This talk is hosted by Dr. Alaa Othmann, Hochschule Bielefeld.

When & where: May 8 2025, 4pm, online, link: https://uni-bielefeld.zoom-x.de/j/64775735478?pwd=TFpEUVFPME5EQXFKMHZHY1ZsM2Y4Zz09

Abstract: In this seminar, Prof. Roveri will explore the transformative potential of the “computing everywhere” paradigm—encompassing the Internet-of-Things and Edge Computing—in driving the widespread adoption of Tiny Machine Learning (TinyML) in daily life. He will present an adaptive perspective on TinyML, focusing on both inference and learning phases directly on-device to address constraints in memory, computation, and energy. The discussion will highlight adaptive mechanisms to optimize processing pipelines dynamically during inference and adaptive training strategies for personalization and evolving environmental demands.

Short bio: Prof. Manuel Roveri is a Full Professor in Computer Engineering at the Dipartimento di Elettronica, Informazione e Bioingegneria of Politecnico di Milano. He is also the Deputy-Chair of the Department. Current research activity addresses Embedded and Edge AI, Learning in presence of Concept Drift and Privacy-preserving Machine Learning. He has published 150+ papers in international journals and conference proceedings and coordinated research and industrial projects for >1.2M euros.