Tree-Based Boosting for Efficient Estimation of S-Parameters for Package Electrical Analysis
We propose a gradient boosted tree surrogate model for S-parameter prediction in high frequency structures with limited training data. Compared to data-hungry neural networks, our approach achieves reasonable accuracy and trains significantly faster.
Authors
- Kemal Aygün (ORCID: https://orcid.org/0000-0002-1701-4746)
- Ahmet C. Durgun (ORCID: https://orcid.org/0000-0002-4802-2271)
- Mustafa Gökçe Baydoğan (ORCID: https://orcid.org/0000-0001-6324-6575)
- Doğanay Özese
Institutions
- Intel (United States) (US)
- Middle East Technical University (TR)
Publication Details
- Published
- 2024-10-06
- DOI
- https://doi.org/10.1109/epeps61853.2024.10753981
- Citations
- 2
- Primary Topic
- Electronic Packaging and Soldering Technologies
- Type
- article
- Field-Weighted Citation Impact
- 0.42
Funders
- Semiconductor Research Corporation