April 5-7, 2022|Santa Clara Convention Center| Santa Clara, CA
Moderator:
Chris Cheng (Distinguished Technologist, HP Enterprise)
Panelists:
Paul D. Franzon, Ph.D., Fellow IEEE (Cirrus Logic Distinguished Professor of Electrical and Computer Engineering, NC State University)
Norman Chang (Ansys Fellow, Ansys)
Osama Waqar Bhatti (P.h.D Candidate, Georgia Institute of Technology)
Todd Westerhoff (Product Marketing Manager , Siemens)
Location: Ballroom G
Date: Wednesday, April 6
Time: 4:00 pm - 5:15 pm
Track: 14. Machine Learning for Microelectronics, Signaling & System Design, 02. Chip I/O & Power Modeling
Format: Panel Discussion
Theme : Infrastructure, Internet of Things (IoT)
Education Level: All
Pass Type: 2-Day Pass, All Access Pass, Expo Pass
Vault Recording: TBD
Audience Level: All
Digital twins have been gaining interest in the AI community as a practical application of using trained AI models to represent complex systems. The generative nature of digital twins allow insights beyond a conventional discriminative simulation model. Being able to capture the joint distribution space of input and output allow an intriguing possibility of reverse modelling (i.e. given a desirable output, what is the maximum likelihood inputs that can generate that results). Another application is data driven modelling with generative adversarial networks (GAN) that use deep learning to generate analysis models simply by observation. Digital twins also allow coupling of multi-physic analysis by combining twins from different models. Real-time digital twins can even allow dynamic adjustment of system performance with a parallel twin performing optimization in real time.
This panel will bring in researchers and practitioner of AI digital twins and discuss their impact on future of SI/PI analysis and EDA business in the future.