Seminar : Machine Learning Based Surrogate Models of Electronic Devices and Circuits

Location :

C108 à l'UFR Sciences et Technique at 10 am .

Abstract :

This talk aims to emphasize the crucial role of cutting-edge data-driven modeling techniques in constructing compact and fast-to-evaluate surrogate models of electronic devices and circuits for stochastic analysis and optimization purposes. Initially, several modeling techniques, such as least-squares regressions, kernel regression, Artificial Neural Networks, and advanced solutions for vector-valued problems, will be briefly presented to highlight their advantages, capabilities, and limitations. Subsequently, in the second part of the presentation, the effectiveness and strength of these techniques will be showcased through applications in uncertainty quantification, optimization, and parametric modeling across various test cases.

Riccardo Trinchero :

He received the M.Sc. and the Ph.D. degrees in Electronics and Communication Engineering from Politecnico di Torino, Torino, Italy, in 2011 and 2015, respectively. He is currently an Associate Professor within the EMC Group with the Department of Electronics and Telecommunications at the Politecnico di Torino. His research interests include the analysis of switching DC-DC converters, machine learning and statistical simulation of circuits and systems.