This paper investigates the application of support vector machine to the modeling of high-speed interconnects with largely varying and/or highly uncertain design parameters. The proposed method relies on a robust and well-established mathematical framework, yielding accurate surrogates of complex dynamical systems. An identification procedure based on the observation of a small set of system responses allows generating compact parametric relations, which can be used for design optimization and/or stochastic analysis. The feasibility and strength of the method are demonstrated based on a benchmark function and on the statistical assessment of a realistic printed circuit board interconnect, highlighting the main features and benefits of this technique over state-of-the-art solutions. Emphasis is given to the effects of the initial sample size and of input noise on the model estimation.
Machine learning for the performance assessment of high-speed links / Trinchero, R.; Manfredi, P.; Stievano, I. S.; Canavero, Flavio G.. - In: IEEE TRANSACTIONS ON ELECTROMAGNETIC COMPATIBILITY. - ISSN 0018-9375. - STAMPA. - 60:6(2018), pp. 1627-1634.
Titolo: | Machine learning for the performance assessment of high-speed links |
Autori: | |
Data di pubblicazione: | 2018 |
Rivista: | |
Digital Object Identifier (DOI): | http://dx.doi.org/10.1109/TEMC.2018.2797481 |
Appare nelle tipologie: | 1.1 Articolo in rivista |
File in questo prodotto:
File | Descrizione | Tipologia | Licenza | |
---|---|---|---|---|
jnl-2018TEMC-SVM.pdf | jnl-2018TEMC-SVM | 2. Post-print / Author's Accepted Manuscript | PUBBLICO - Tutti i diritti riservati | Visibile a tuttiVisualizza/Apri |
jnl-2018TEMC-SVM-IEEE.pdf | jnl-2018TEMC-SVM-IEEE | 2. Post-print / Author's Accepted Manuscript | Non Pubblico - Accesso privato/ristretto | Administrator Richiedi una copia |
http://hdl.handle.net/11583/2715089