TY - GEN
T1 - Explaining and interpreting machine learning CAD decisions
T2 - 2nd ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2020
AU - Krishnamurthy, Prashanth
AU - Chowdhury, Animesh Basak
AU - Tan, Benjamin
AU - Khorrami, Farshad
AU - Karri, Ramesh
N1 - Funding Information:
This work was supported in part by ONR Award # N00014-18-1-2672 and DARPA grant # FA8750-20-1-0502. B. Tan and R. Karri are supported in part by ONR Award # N00014-18-1-2058. R. Karri is supported in part by the NYU/NYUAD Center for Cyber Security.
Publisher Copyright:
© 2020 Association for Computing Machinery.
PY - 2020/11/16
Y1 - 2020/11/16
N2 - We provide a methodology to explain and interpret machine learning decisions in Computer-Aided Design (CAD) flows. We demonstrate the efficacy of the methodology to the VLSI testing case. Such a tool will provide designers with insight into the "black box" machine learning models/classifiers through human readable sentences based on normally understood design rules or new design rules. The methodology builds on an intrinsically explainable, rule-based ML framework, called Sentences in Feature Subsets (SiFS), to mine human readable decision rules from empirical data sets. SiFS derives decision rules as compact Boolean logic sentences involving subsets of features in the input data. The approach is applied to test point insertion problem in circuits and compared to the ground truth and traditional design rules.
AB - We provide a methodology to explain and interpret machine learning decisions in Computer-Aided Design (CAD) flows. We demonstrate the efficacy of the methodology to the VLSI testing case. Such a tool will provide designers with insight into the "black box" machine learning models/classifiers through human readable sentences based on normally understood design rules or new design rules. The methodology builds on an intrinsically explainable, rule-based ML framework, called Sentences in Feature Subsets (SiFS), to mine human readable decision rules from empirical data sets. SiFS derives decision rules as compact Boolean logic sentences involving subsets of features in the input data. The approach is applied to test point insertion problem in circuits and compared to the ground truth and traditional design rules.
KW - IC Testing
KW - Interpretable Machine Learning
KW - Test-Point Insertion
UR - http://www.scopus.com/inward/record.url?scp=85098267653&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85098267653&partnerID=8YFLogxK
U2 - 10.1145/3380446.3430643
DO - 10.1145/3380446.3430643
M3 - Conference contribution
AN - SCOPUS:85098267653
T3 - MLCAD 2020 - Proceedings of the 2020 ACM/IEEE Workshop on Machine Learning for CAD
SP - 129
EP - 134
BT - MLCAD 2020 - Proceedings of the 2020 ACM/IEEE Workshop on Machine Learning for CAD
PB - Association for Computing Machinery, Inc
Y2 - 16 November 2020 through 20 November 2020
ER -