Adaptive ensemble optimization for memory-related hyperparameters in retraining DNN at edge

Yidong Xu, Rui Han, Xiaojiang Zuo, Junyan Ouyang, Chi Harold Liu, Lydia Y. Chen

Abstract: Highlights•Propose a lightweight in-memory hyperparameter tuning method for retraining.•Improve deployment efficiency by implementing an online resource profiler.•Achieve continuous training accuracy improvement by using a rule engine.•Suitable for multiple DNN networks and various edge device scenarios.