Presentation
FuNToM: Functional Modeling of RF Circuits Using a Neural Network Assisted Two-port Analysis Method
DescriptionIn this paper, we present FANToM, a functional modeling tool for Analog and Mixed-Signal (AMS) circuits. FANToM uses the two-port analysis method for decreasing the number of design parameters and ultimately the dimensionality of the model. It also leverages neural networks which have shown promising results in predicting the behavior of AMS circuits. Our results show that for multiple AMS circuits, in comparison to the state-of-the-art works while maintaining the same accuracy, the required training data is reduced by 7.3x-76.4x. In addition, FANToM needs 176.8x-188.6x less time for collecting the training set in post-layout modeling.
Event Type
Work-in-Progress Poster
TimeTuesday, July 11th6:00pm - 7:00pm PDT
LocationLevel 2 Lobby
AI
Autonomous Systems
Cloud
Design
EDA
Embedded Systems
RISC-V
Security