21 maggio 2026 | 14:15
Dipartimento di Elettronica, Informazione e Bioingegneria – Politecnico di Milano
Sala Schiavoni (edificio 20A)
Speaker: Dušan M. Stipanović (Professor, Arthur Davis Scholar, Coordinated Science Laboratory and Department of Industrial and Enterprise Systems Engineering, University of Illinois Urbana-Champaign)
Sommario
In this talk, the training of both feedforward and recurrent neural networks in machine learning will be considered from the control theory prospective.
The training problem formulation is practically an optimal control problem of the tracking type and thus there is a link to the well-known control problem of regulation.
Furthermore, some connections to the control regulator schemes, particularly internal model control regulation, will be presented
Biografia
Dr. Dušan Stipanović received his B.S. degree in electrical engineering from the University of Belgrade, Belgrade, Serbia, in 1994, and the M.S.E.E. and Ph.D. degrees in electrical engineering from Santa Clara University, Santa Clara, California, in 1996 and 2000, respectively.
Dr. Stipanović had been an Adjunct Lecturer and Research Associate with the Department of Electrical Engineering at Santa Clara University (1998-2001), and a Research Associate in Professor Claire Tomlin’s Hybrid Systems Laboratory of the Department of Aeronautics and Astronautics at Stanford University (2001-2004). In 2004 he joined the University of Illinois at Urbana-Champaign where he is now Professor in the Controls Group of the Coordinated Science Laboratory and Department of Industrial and Enterprise Systems Engineering.
He is a visiting Professor in the School of Electrical Engineering of the University of Belgrade in Serbia. He also held visiting faculty positions in the EECS Department at the University of California at Berkeley and in the Robotics and Telematics Department at the University of Würzburg in Germany.
His research interests include decentralized control and estimation, stability theory, optimal control, and differential games with applications in control of autonomous vehicles, precision agriculture, circuits, robotics, and machine learning.
Dr. Stipanović served as an Associate Editor on the Editorial Boards of the IEEE Transactions on Circuits and Systems I and II, and Journal of Optimization Theory and Applications. He is a recipient of the Bessel Award in Mathematics (calculus of variations and control theory) from the Humboldt Foundation and 1000 Talents Award from the People’s Republic of China, and is a fellow of IEEE.