Learning to Design Analog Circuits to Meet Threshold Specifications

TL;DR

This paper introduces a supervised learning approach for automated analog circuit design that efficiently generates circuits meeting threshold specifications, outperforming prior methods in success rate and data efficiency across diverse circuit types.

Contribution

It presents a novel method for training models on simulation data to design circuits meeting threshold criteria, with extensive evaluation across various circuit configurations.

Findings

Success rate over 90% at 5% error margin

Significant improvement in data efficiency (up to 10x)

Validated on diverse linear, nonlinear, and autonomous circuits

Abstract

Automated design of analog and radio-frequency circuits using supervised or reinforcement learning from simulation data has recently been studied as an alternative to manual expert design. It is straightforward for a design agent to learn an inverse function from desired performance metrics to circuit parameters. However, it is more common for a user to have threshold performance criteria rather than an exact target vector of feasible performance measures. In this work, we propose a method for generating from simulation data a dataset on which a system can be trained via supervised learning to design circuits to meet threshold specifications. We moreover perform the to-date most extensive evaluation of automated analog circuit design, including experimenting in a significantly more diverse set of circuits than in prior work, covering linear, nonlinear, and autonomous circuit configurations, and show that our method consistently reaches success rate better than 90% at 5% error margin, while also improving data efficiency by upward of an order of magnitude. A demo of this system is available at circuits.streamlit.app