A comprehensive AI-driven research program for fully automated analog circuit design — from performance specification to manufacturable layout.
Designing analog and RF circuits remains one of the most expertise-intensive and time-consuming challenges in modern electronics. The FALCON research program addresses this bottleneck by developing AI-driven methods for end-to-end analog circuit design, enabling the transition from specification to manufacturable layout.
Our work focuses on scalable learning-based models, large-scale datasets, and physics- and layout-aware optimization, with the goal of enabling reliable, generalizable, and automated design across diverse circuit topologies.
Dive into the details of our research program across four dedicated sections.
Explore our AI-driven design pipeline, including topology selection, learned performance modeling, and layout-aware optimization.
A collection of interconnected papers forming a cohesive research ecosystem.
Open-source datasets for analog circuit design, including large-scale simulations across diverse circuit topologies.
A collaborative effort between USC and UCI, advancing state-of-the-art AI-driven analog circuit design.
Interested in using FALCON for your analog circuit design needs? We welcome collaborations with research groups, universities, and industry partners.
Contact us with your circuit specifications or to discuss a custom AI solution for your research group. Whether you need topology selection, performance prediction, or end-to-end layout design, we’d love to hear from you.
mehradfa@usc.edu