Title:
Design Space Extrapolation and Inverse Design using Machine Learning
Design Space Extrapolation and Inverse Design using Machine Learning
| dc.contributor.advisor | Swaminathan, Madhavan | |
| dc.contributor.author | Bhatti, Osama Waqar | |
| dc.contributor.committeeMember | Raychowdhury, Arijit | |
| dc.contributor.committeeMember | Mukhopadhyay, Saibal | |
| dc.contributor.committeeMember | Lim, Sung-kyu | |
| dc.contributor.department | Electrical and Computer Engineering | |
| dc.date.accessioned | 2023-01-10T16:24:20Z | |
| dc.date.available | 2023-01-10T16:24:20Z | |
| dc.date.created | 2022-12 | |
| dc.date.issued | 2022-12-13 | |
| dc.date.submitted | December 2022 | |
| dc.date.updated | 2023-01-10T16:24:21Z | |
| dc.description.abstract | Modern electronic systems need to be analyzed and designed carefully for their operation at higher frequencies and many control parameters. This process takes up a huge time for computations and design cycles. To this effect, in this webinar, we investigate machine learning techniques for power delivery, signal integrity and EM problems. More specifically, we present two broad design strategies. Often one needs to predict the structure behavior outside the range of simulations. This work deals with extrapolation in two domains. (1) We propose HilbertNet for complex-valued causal extrapolation of frequency responses. The proposed architecture accurately predicts the out-of-band frequency response by modelling the temporal correlations between in-band frequency samples using specialized recurrent neural networks. (2) We propose Transposed Convolutional Networks to model spatial correlations in the design space. The design space comprises of all the geometrical and material parameters characterizing the response. The convolutional networks can extrapolate the design space in as high as 11 dimensions because of inducing spatial bias into the model. These techniques constitute forward design. We also present some recent methods developed for inverse design of electronic systems. The goal in inverse design is to estimate the best set of design space values that generate the response space. We employ invertible neural networks to model the non-linear mapping between the design space and the response space. We show the effectiveness of these techniques in signal and power integrity applications. | |
| dc.description.degree | Ph.D. | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.uri | http://hdl.handle.net/1853/70146 | |
| dc.language.iso | en_US | |
| dc.publisher | Georgia Institute of Technology | |
| dc.subject | Machine learning | |
| dc.subject | Bayes theorem | |
| dc.subject | Neural networks | |
| dc.subject | Signal integrity | |
| dc.subject | Power delivery | |
| dc.subject | High speed channel | |
| dc.subject | Eye diagram | |
| dc.title | Design Space Extrapolation and Inverse Design using Machine Learning | |
| dc.type | Text | |
| dc.type.genre | Dissertation | |
| dspace.entity.type | Publication | |
| local.contributor.advisor | Swaminathan, Madhavan | |
| local.contributor.corporatename | School of Electrical and Computer Engineering | |
| local.contributor.corporatename | College of Engineering | |
| relation.isAdvisorOfPublication | 974f4642-b132-43e2-9ca6-c40e8af82f93 | |
| relation.isOrgUnitOfPublication | 5b7adef2-447c-4270-b9fc-846bd76f80f2 | |
| relation.isOrgUnitOfPublication | 7c022d60-21d5-497c-b552-95e489a06569 | |
| thesis.degree.level | Doctoral |