Scheduling IDK classifiers with arbitrary dependences to minimize the expected time to successful classification
Abdelzaher, T., Agrawal, K., Baruah, S., Burns, A., Davis, R. I. I., Guo, Z., & Hu, Y. (2023, March 13). REAL-TIME SYSTEMS.
author keywords: Real-time; Classifiers; Optimal ordering; DNN; Arbitrary dependences
TL;DR:
Optimal algorithms are developed for sequentially ordering IDK classifiers into an IDK cascade, such that the expected duration to successfully classify an input is minimized, optionally subject to a latency constraint on the worst-case overall execution duration of the IDK cascade.
(via
Semantic Scholar)
UN Sustainable Development Goal Categories