Ph.D. Proposal Oral Exam - Huan Yu

Event Details

Tuesday, October 2, 2018

10:30am - 12:30pm

Location: 
Room 1123, Klaus

For More Information

Contact:

Event Details

Title:  Behavioral Modeling of Drivers and Oscillators Using Machine Learning

Committee: 

Dr. Swaminathan, Advisor      

Dr. Lim, Chair

Dr. Raychowdhury

Abstract:

The objective of the proposed research is to develop time-domain component-level behavioral models for drivers and oscillators for fast simulation and IP protection. For drivers, parametric modeling approaches are used, and the dynamic memory characteristics of the driver’s output stage are captured using recurrent neural networks (RNNs). For oscillators, augmented neural networks (AugNNs) are proposed to capture the oscillatory behavior of fixed-frequency oscillators and VCOs. The proposed models are compatible with Verilog-A.

Last revised September 28, 2018