Ensemble Active Learning by Contextual Bandits for AI Incubation in Manufacturing
This addresses the problem of maintaining data quality with less annotation for AI applications in manufacturing, but it appears incremental as it combines existing techniques like ensemble active learning and contextual bandits.
The paper tackles the challenge of reducing annotation efforts in streaming data acquisition for supervised learning by proposing an ensemble active learning method using contextual bandits, which enforces an exploration-exploitation balance and leads to improved AI modeling performance.
It is challenging but important to save annotation efforts in streaming data acquisition to maintain data quality for supervised learning base learners. We propose an ensemble active learning method to actively acquire samples for annotation by contextual bandits, which is will enforce the exploration-exploitation balance and leading to improved AI modeling performance.