Published: June 17, 2024
Citation: Computer (IEEE Computer) vol. 57, no. 7, (July 2024) pp. 16-26
Author(s)
Jaganmohan Chandrasekaran (Virginia Tech), Erin Lanus (Virginia Tech), Tyler Cody (Virginia Tech), Laura Freeman (Virginia Tech), Raghu Kacker (NIST), M S Raunak (NIST), Richard Kuhn (NIST)
The data-intensive nature of machine learning (ML)-enabled systems introduces unique challenges in test and evaluation. We present an overview of combinatorial coverage, exploring its applications across the ML-enabled system lifecycle and its potential to address key limitations in performing test and evaluation for ML-enabled systems.
The data-intensive nature of machine learning (ML)-enabled systems introduces unique challenges in test and evaluation. We present an overview of combinatorial coverage, exploring its applications across the ML-enabled system lifecycle and its potential to address key limitations in performing test...
See full abstract
The data-intensive nature of machine learning (ML)-enabled systems introduces unique challenges in test and evaluation. We present an overview of combinatorial coverage, exploring its applications across the ML-enabled system lifecycle and its potential to address key limitations in performing test and evaluation for ML-enabled systems.
Hide full abstract
Keywords
Machine Learning; Combinatorial Coverage; Combinatorial Testing; Test generation; Model Maintenance; Regression Testing
Control Families
None selected
