AICircuit: A Multi-Level Dataset and Benchmark for AI-Driven Analog Integrated Circuit Design

Analog and radio-frequency circuit design requires extensive exploration of both circuit topology and parameters to meet specific design criteria. This design process is highly specialized and time-intensive, particularly as the number of circuit parameters increases and the circuit becomes more complex. Prior research has explored the potential of machine learning to enhance circuit design procedures; however, primarily focused on simple circuits. To date, a generic and diverse dataset with robust metrics on advanced mm-wave circuits does not exist. To bridge this gap, we present AICircuit, a comprehensive multi-level dataset and benchmark for developing and evaluating ML algorithms in analog and radio-frequency circuit design. AICircuit comprises seven commonly used advanced analog circuits and two complex wireless transceiver systems composed of multiple circuit blocks, encompassing a wide array of design scenarios encountered in real-world applications. We extensively evaluate various ML algorithms on the dataset, revealing the potential of ML algorithms in learning the mapping from the design specifications to the desired circuit parameters.

In The Machine Learning and the Physical Sciences Workshop @ NeurIPS