The Effects of Weight Quantization on Online Federated Learning for the IoT: A Case Study

Autor: Nil Llisterri Gimenez, Junkyu Lee, Felix Freitag, Hans Vandierendonck

Publikováno v: IEEE Access, Vol 12, Pp 5490-5502 (2024)

Many weight quantization approaches were explored to save the communication bandwidth between the clients and the server in federated learning using high-end computing machines. However, there is a lack of weight quantization research for online fede

Externí odkaz: https://doaj.org/article/d7f3178eb1934215955a42380cb29836

Increased Leverage of Transprecision Computing for Machine Vision Applications at the Edge

Autor: Umar Ibrahim Minhas, JunKyu Lee, Lev Mukhanov, Georgios Karakonstantis, Hans Vandierendonck, Roger Woods

Publikováno v: Minhas, U, Lee, J, Mukhanov, L, Karakonstantis, G, Vandierendonck, H & Woods, R 2022, ' Increased Leverage of Transprecision Computing for Machine Vision Applications at the Edge ', Journal of Signal Processing Systems, vol. 94, pp. 1101-1118 .

The practical deployment of machine vision presents particular challenges for resource constrained edge devices. With a clear need to execute multiple tasks with variable workloads, there is a need for a robust approach that can dynamically adapt at

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b048905dff6b270df501ac9da7b77859
https://doi.org/10.1007/s11265-022-01784-1

ROMA: run-time object detection to maximize real-time accuracy

Autor: JunKyu Lee, Blesson Varghese, Hans Vandierendonck

Publikováno v: Lee, J, Varghese, B & Vandierendonck, H 2023, ROMA: run-time object detection to maximize real-time accuracy . in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023 . IEEE/CVF Winter Conference on Applications of Computer Vision (WACV): Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 6394-6403, IEEE Winter Conference on Applications of Computer Vision, Waikoloa, Hawaii, United States, 02/01/2023 . https://doi.org/10.1109/wacv56688.2023.00634

This paper analyzes the effects of dynamically varying video contents and detection latency on the real-time detection accuracy of a detector and proposes a new run-time accuracy variation model, ROMA, based on the findings from the analysis. ROMA is

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::139b6ede175c3fd4d1183e22eeae91ed
https://pure.qub.ac.uk/en/publications/17d72226-40c7-426c-a108-1332915983b4

MASTIFF: structure-aware minimum spanning tree/forest

Autor: Peter Kilpatrick, Hans Vandierendonck, Mohsen Koohi Esfahani

Publikováno v: Koohi Esfahani, M, Kilpatrick, P & Vandierendonck, H 2022, MASTIFF: structure-aware minimum spanning tree/forest . in Proceedings of the 36th ACM International Conference on Supercomputing, ICS 2022 ., 9, ACM International Conference on Supercomputing: Proceedings, Association for Computing Machinery, 36th ACM International Conference on Supercomputing, virtual, online, 28/06/2022 . https://doi.org/10.1145/3524059.3532365

The Minimum Spanning Forest (MSF) problem finds usage in many different applications. While theoretical analysis shows that linear-time solutions exist, in practice, parallel MSF algorithms remain computationally demanding due to the continuously inc

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d3c91aba25805a40f130055033736f7f
https://pure.qub.ac.uk/en/publications/456f85fe-6f36-4d50-a61d-2ee0feb97265

SAPCo Sort: Optimizing Degree-Ordering for Power-Law Graphs

Autor: Mohsen Koohi Esfahani, Peter Kilpatrick, Hans Vandierendonck

Publikováno v: 2022 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS).

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::1d68232defa880cbfabaf8c78f434523
https://doi.org/10.1109/ispass55109.2022.00015