FairCanary
Avijit Ghosh, Aalok Shanbhag, Christo Wilson
Abstract
Systems that offer continuous model monitoring have emerged in response to (1) well-documented failures of deployed Machine Learning (ML) and Artificial Intelligence (AI) models and (2) new regulatory requirements impacting these models. Existing monitoring systems continuously track the performance of deployed ML models and compute feature importance (a.k.a. explanations) for each prediction to help developers identify the root causes of emergent model performance problems.
Topics & Concepts
Computer scienceFeature (linguistics)Artificial intelligenceTrack (disk drive)Root (linguistics)Root causeMachine learningEngineeringReliability engineeringOperating systemPhilosophyLinguisticsExplainable Artificial Intelligence (XAI)Adversarial Robustness in Machine LearningEthics and Social Impacts of AI