CMAS Lab - Exploring the Impact of Parametric Variability on Eye

Journal article

K. Dimple, Surila Guglani, Rahul Kumar, Sourajeet Roy, Brajesh Kumar Kaushik, Suyash Kushwaha, Rohit Sharma
Electronic Components and Technology Conference, 2022

Semantic Scholar DOI

Cite

APA Click to copy
Dimple, K., Guglani, S., Kumar, R., Roy, S., Kaushik, B. K., Kushwaha, S., & Sharma, R. (2022). Exploring the Impact of Parametric Variability on Eye Diagram of On-Chip Multi-walled Carbon Nanotube Interconnects using Fast Machine Learning Techniques. Electronic Components and Technology Conference.

Chicago/Turabian Click to copy
Dimple, K., Surila Guglani, Rahul Kumar, Sourajeet Roy, Brajesh Kumar Kaushik, Suyash Kushwaha, and Rohit Sharma. “Exploring the Impact of Parametric Variability on Eye Diagram of On-Chip Multi-Walled Carbon Nanotube Interconnects Using Fast Machine Learning Techniques.” Electronic Components and Technology Conference (2022).

MLA Click to copy
Dimple, K., et al. “Exploring the Impact of Parametric Variability on Eye Diagram of On-Chip Multi-Walled Carbon Nanotube Interconnects Using Fast Machine Learning Techniques.” Electronic Components and Technology Conference, 2022.

BibTeX Click to copy

@article{k2022a,
  title = {Exploring the Impact of Parametric Variability on Eye Diagram of On-Chip Multi-walled Carbon Nanotube Interconnects using Fast Machine Learning Techniques},
  year = {2022},
  journal = {Electronic Components and Technology Conference},
  author = {Dimple, K. and Guglani, Surila and Kumar, Rahul and Roy, Sourajeet and Kaushik, Brajesh Kumar and Kushwaha, Suyash and Sharma, Rohit}
}

Abstract

In this paper, an artificial neural network (ANN) based metamodel is developed for estimating the eye diagram characteristics of on-chip multi-walled carbon nanotube (MWCNT) interconnect networks subject to parametric variability. The proposed ANN metamodel is trained using a prior knowledge input with source difference (PKID) formulation. In this PKID formulation, the eye diagram characteristics predicted by the compact but approximate equivalent single conductor (ESC) representation of the MWCNT conductors is used as prior knowledge to accelerate the learning of the ANN. Consequently, the proposed ANN metamodel can be trained at far smaller computational time costs than conventional ANN metamodels and existing multi-fidelity approaches without any discernable loss in accuracy.