no code implementations • 14 Feb 2024 • Hong Jia, Young D. Kwon, Dong Ma, Nhat Pham, Lorena Qendro, Tam Vu, Cecilia Mascolo
This limitation hinders the feasibility of many important on-device wearable event detection (WED) applications, such as heart attack detection.
no code implementations • 19 Nov 2023 • Young D. Kwon, Jagmohan Chauhan, Hong Jia, Stylianos I. Venieris, Cecilia Mascolo
With respect to the state-of-the-art (SOTA) Meta CL method, LifeLearner drastically reduces the memory footprint (by 178. 7x), end-to-end latency by 80. 8-94. 2%, and energy consumption by 80. 9-94. 2%.
no code implementations • 19 Jul 2023 • Young D. Kwon, Rui Li, Stylianos I. Venieris, Jagmohan Chauhan, Nicholas D. Lane, Cecilia Mascolo
On-device training is essential for user personalisation and privacy.
no code implementations • 9 Jun 2022 • Anish K. Vallapuram, Pengyuan Zhou, Young D. Kwon, Lik Hang Lee, Hengwei Xu, Pan Hui
Consequently, the training requires high computation cost and a long time to converge while the model performance does not pay off.
no code implementations • 8 Mar 2022 • Young D. Kwon, Jagmohan Chauhan, Cecilia Mascolo
In this paper, we propose YONO, a product quantization (PQ) based approach that compresses multiple heterogeneous models and enables in-memory model execution and switching for dissimilar multi-task learning on MCUs.
no code implementations • 21 Feb 2022 • Anish Das, Young D. Kwon, Jagmohan Chauhan, Cecilia Mascolo
Deep Learning (DL) has shown impressive performance in many mobile applications.
no code implementations • 25 Oct 2021 • Young D. Kwon, Jagmohan Chauhan, Abhishek Kumar, Pan Hui, Cecilia Mascolo
Our findings suggest that replay with exemplars-based schemes such as iCaRL has the best performance trade-offs, even in complex scenarios, at the expense of some storage space (few MBs) for training examples (1% to 5%).
no code implementations • 14 Jun 2021 • Young D. Kwon, Jagmohan Chauhan, Cecilia Mascolo
Various incremental learning (IL) approaches have been proposed to help deep learning models learn new tasks/classes continuously without forgetting what was learned previously (i. e., avoid catastrophic forgetting).
no code implementations • 6 Jun 2021 • Sandra Servia-Rodriguez, Cecilia Mascolo, Young D. Kwon
Our experiments prove the robustness and reliability of the learned models to adapt to the changing sensing environment, and show the suitability of using uncertainty of the predictions to assess their reliability.