Robust Rare Circuit Failure Detection using Data-Efficient Machine Learning


Peng Li (University of California Santa Barbara)


Anomaly detection has become an increasingly important research problem and challenge with applications in many science and engineering domains. Advances in anomaly detection can broadly impact a broad range of use cases including verification of mission/safety-critical systems, robust manufacturing, predictive maintenance, and fraud detection.

This talk will present machine learning techniques targeting detection of rare circuit failures using severely limited amounts of training data for reasons such as high cost in data collection and/or unavailability of labeled data. As such, the key challenge to be tackled is to enable anomaly detection with desired data efficiency and robustness in high-dimensional input (feature) spaces where complex interactions of such features lead to rareness of failures.

First, we will present a data-efficient Bayesian optimization (BO) approach. At the heart of the proposed BO process is a delicate balancing between two competing needs: exploitation of the current statistical model for quick identification of highly likely failures and exploration of undiscovered feature space so as to detect hard-to-find failures over wide ranges of feature values. While one of the key benefits of BO is its generality as a black-box solution, existing BO techniques do not scale well with the dimensionality of the feature space. Dimension reduction, a key enabler for scaling learning in a high-dimensional feature space, will be introduced under the framework of Bayesian optimization. Second, a self-labeling approach for unsupervised learning and detection of anomalies where no labeled training data is assumed will be presented. Finally, general issues of robust machine learning in terms of model uncertainty and resilience with respect to various local and global attacks will be discussed. The proposed amorally detection techniques will be demonstrated under the context of analog/mixed-signal IC design verification and post-manufacturing test for safety-critical automotive applications with stringent failure rate requirements, e.g. less than one detective parts per million (DPPM).


Peng Li received the Ph. D. degree from Carnegie Mellon University in 2003. He was on the faculty of Texas A&M University from August 2004 to June 2019. Since July 2019, he has been with the University of California at Santa Barbara as a professor of Electrical and Computer Engineering.

His research interests are in integrated circuits and systems, electronic design automation, brain-inspired computing, and robust machine learning. Li’s work has been recognized by an ICCAD Ten Year Retrospective Most Influential Paper Award, four IEEE/ACM Design Automation Conference (DAC) Best Paper Awards, an Honorary Mention Best Paper Award from ISCAS, an IEEE/ACM William J. McCalla ICCAD Best Paper Award, two SRC Inventor Recognition Awards, two MARCO Inventor Recognition Awards, and an NSF CAREER Award. He was honored by the ECE Outstanding Professor Award, and was named the TEES Fellow, William O. and Montine P. Head Faculty Fellow, and Eugene Webb Fellow by the College of Engineering at Texas A&M University. He was the Vice President for Technical Activities of the IEEE Council on Electronic Design Automation from Jan. 2016 to Dec. 2017. He is a Fellow of the IEEE and has consulted for Intel and two Silicon Valley startup companies.