Fast Extraction of Per-Unit-Length Parameters of Hybrid Copper-Graphene Interconnects via Generalized Knowledge Based Machine Learning

In this paper, a knowledge-based machine learning technique has been presented for estimating the per-unit-length parameters of hybrid copper-graphene interconnect networks. The salient feature of the proposed technique is its ability to be trained using significantly smaller amounts of full-wave electromagnetic (EM) solver data compared to conventional machine learning regression techniques, such as artificial neural networks (ANNs) and support vector machines (SVMs).