Machine Learning for the Performance Assessment of High-Speed Links
| Autor: | Flavio Canavero, Riccardo Trinchero, Paolo Manfredi, Igor Simone Stievano |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Dynamical systems theory
Computer science Stochastic process High-speed interconnect Emphasis (telecommunications) Uncertainty 020206 networking & telecommunications Control engineering 02 engineering and technology Function (mathematics) Condensed Matter Physics Atomic and Molecular Physics and Optics 020202 computer hardware & architecture Support vector machine Noise Machine learning Parameterized modeling Support vector machine (SVM) regression Electrical and Electronic Engineering Atomic and Molecular Physics 0202 electrical engineering electronic engineering information engineering Benchmark (computing) and Optics Parametric statistics |
| Zdroj: | IEEE Transactions on Electromagnetic Compatibility. 60:1627-1634 |
| ISSN: | 1558-187X 0018-9375 |
| DOI: | 10.1109/temc.2018.2797481 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|