Application of SVM for Design Optimization of High-Speed Links
Machine Learning (ML) methods are a mature alternative that have been seldom applied to to the modeling of high-speed interconnects with largely varying and/or highly uncertain design parameters. Support vector machine (SVM) is probably one of the most popular examples of ML, with applications for both classi?cation and regression. This approach relies on a strong mathematical background and is already supplemented by ready-to-use algorithms embedded in almost any software for data processing. This workshop is intended for design engineers who want to gain a better understanding of the SVM technique and of its advantages and limitations w.r.t. other approaches having similar features. The feasibility and strengths of the method are demonstrated based on benchmarks and on the statistical assessment of realistic printed circuit board interconnects, highlighting the main features and bene?ts of this technique other over state-of-the-art solutions.
Flavio Canavero, Politecnico di Torino
Flavio G. Canavero received his electronic engineering Master degree from Politecnico (Technical University) of Torino, Italy, in 1977 and the Ph.D. degree from the School of Geophysical Sciences of Georgia Institute of Technology, Atlanta, USA, in 1986. He is currently a Professor of circuit theory with the Department of Electronics and Telecommunications, Politecnico di Torino, where he is also the Director of the Doctoral School. His research interests include signal integrity and EMC design issues, interconnect modeling, black-box characterization of digital integrated circuits, and EMI and statistics EMC. Dr. Canavero was a recipient of several industrial and IEEE Awards, including the prestigious Richard R. Stoddard Award for Outstanding Performance, which is the EMC Society's highest technical award, and the Honored Member Award of the EMC Society. He has been the Editor-in-Chief for the IEEE TRANSACTIONS ON ELECTROMAGNETIC COMPATIBILITY, the V.P. for Communication Services of the EMC Society, and the Chair of the URSI Commission E.