Data-driven Compact Models for Circuit Design and Analysis

K. Aadithya, P. Kuberry, B. Paskaleva, P. Bochev, K. Leeson, A. Mar, T. Mei, E. Keiter
Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:555-569, 2020.

Abstract

Compact semiconductor device models are essential for efficiently designing and analyzing large circuits. However, traditional compact model development requires a large amount of manual effort and can span many years. Moreover, inclusion of new physics (\eg{}, radiation effects) into an existing model is not trivial and may require redevelopment from scratch. Machine Learning (ML) techniques have the potential to automate and significantly speed up the development of compact models. In addition, ML provides a range of modeling options that can be used to develop hierarchies of compact models tailored to specific circuit design stages. In this paper, we explore three such options: (1) table-based interpolation, (2) Generalized Moving Least-Squares, and (3) feed-forward Deep Neural Networks, to develop compact models for a p-n junction diode. We evaluate the performance of these “data-driven” compact models by (1) comparing their voltage-current characteristics against laboratory data, and (2) building a bridge rectifier circuit using these devices, predicting the circuit’s behavior using SPICE-like circuit simulations, and then comparing these predictions against laboratory measurements of the same circuit.

Cite this Paper

BibTeX
@InProceedings{pmlr-v107-aadithya20a, title = {Data-driven Compact Models for Circuit Design and Analysis}, author = {Aadithya, K. and Kuberry, P. and Paskaleva, B. and Bochev, P. and Leeson, K. and Mar, A. and Mei, T. and Keiter, E.}, booktitle = {Proceedings of The First Mathematical and Scientific Machine Learning Conference}, pages = {555--569}, year = {2020}, editor = {Lu, Jianfeng and Ward, Rachel}, volume = {107}, series = {Proceedings of Machine Learning Research}, month = {20--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v107/aadithya20a/aadithya20a.pdf}, url = {https://proceedings.mlr.press/v107/aadithya20a.html}, abstract = {Compact semiconductor device models are essential for efficiently designing and analyzing large circuits. However, traditional compact model development requires a large amount of manual effort and can span many years. Moreover, inclusion of new physics (\eg{}, radiation effects) into an existing model is not trivial and may require redevelopment from scratch. Machine Learning (ML) techniques have the potential to automate and significantly speed up the development of compact models. In addition, ML provides a range of modeling options that can be used to develop hierarchies of compact models tailored to specific circuit design stages. In this paper, we explore three such options: (1) table-based interpolation, (2) Generalized Moving Least-Squares, and (3) feed-forward Deep Neural Networks, to develop compact models for a p-n junction diode. We evaluate the performance of these “data-driven” compact models by (1) comparing their voltage-current characteristics against laboratory data, and (2) building a bridge rectifier circuit using these devices, predicting the circuit’s behavior using SPICE-like circuit simulations, and then comparing these predictions against laboratory measurements of the same circuit. } }
Endnote
%0 Conference Paper %T Data-driven Compact Models for Circuit Design and Analysis %A K. Aadithya %A P. Kuberry %A B. Paskaleva %A P. Bochev %A K. Leeson %A A. Mar %A T. Mei %A E. Keiter %B Proceedings of The First Mathematical and Scientific Machine Learning Conference %C Proceedings of Machine Learning Research %D 2020 %E Jianfeng Lu %E Rachel Ward %F pmlr-v107-aadithya20a %I PMLR %P 555--569 %U https://proceedings.mlr.press/v107/aadithya20a.html %V 107 %X Compact semiconductor device models are essential for efficiently designing and analyzing large circuits. However, traditional compact model development requires a large amount of manual effort and can span many years. Moreover, inclusion of new physics (\eg{}, radiation effects) into an existing model is not trivial and may require redevelopment from scratch. Machine Learning (ML) techniques have the potential to automate and significantly speed up the development of compact models. In addition, ML provides a range of modeling options that can be used to develop hierarchies of compact models tailored to specific circuit design stages. In this paper, we explore three such options: (1) table-based interpolation, (2) Generalized Moving Least-Squares, and (3) feed-forward Deep Neural Networks, to develop compact models for a p-n junction diode. We evaluate the performance of these “data-driven” compact models by (1) comparing their voltage-current characteristics against laboratory data, and (2) building a bridge rectifier circuit using these devices, predicting the circuit’s behavior using SPICE-like circuit simulations, and then comparing these predictions against laboratory measurements of the same circuit.
APA
Aadithya, K., Kuberry, P., Paskaleva, B., Bochev, P., Leeson, K., Mar, A., Mei, T. & Keiter, E.. (2020). Data-driven Compact Models for Circuit Design and Analysis. Proceedings of The First Mathematical and Scientific Machine Learning Conference, in Proceedings of Machine Learning Research 107:555-569 Available from https://proceedings.mlr.press/v107/aadithya20a.html.

Related Material