https://scholars.lib.ntu.edu.tw/handle/123456789/611190
標題: | MulTa-HDC: A Multi-Task Learning Framework for Hyperdimensional Computing | 作者: | AN-YEU(ANDY) WU | 關鍵字: | Brain-inspired computing; hyperdimensional computing; machine learning; multi-task learning | 公開日期: | 2021 | 卷: | 70 | 期: | 8 | 起(迄)頁: | 1269-1284 | 來源出版物: | IEEE Transactions on Computers | 摘要: | Brain-inspired Hyperdimensional computing (HDC) has shown its effectiveness in low-power/energy designs for edge computing in the Internet of Things (IoT). Due to limited resources available on edge devices, multi-task learning (MTL), which accommodates multiple cognitive tasks in one model, is considered a more efficient deployment of HDC. However, as the number of tasks increases, MTL-based HDC (MTL-HDC) suffers from the huge overhead of associative memory (AM) and performance degradation. This hinders MTL-HDC from the practical realization on edge devices. This article aims to establish an MTL framework for HDC to achieve a flexible and efficient trade-off between memory overhead and performance degradation. For the shared-AM approach, we propose Dimension Ranking for Effective AM Sharing (DREAMS) to effectively merge multiple AMs while preserving as much information of each task as possible. For the independent-AM approach, we propose Dimension Ranking for Independent MEmory Retrieval (DRIMER) to extract and concatenate informative components of AMs while mitigating interferences among tasks. By leveraging both mechanisms, we propose a hybrid framework of Multi-Tasking HDC, called MulTa-HDC. To adapt an MTL-HDC system to an edge device given a memory resource budget, MulTa-HDC utilizes three parameters to flexibly adjust the proportion of the shared AM and independent AMs. The proposed MulTa-HDC is widely evaluated across three common benchmarks under two standard task protocols. The simulation results of ISOLET, UCIHAR, and MNIST datasets demonstrate that the proposed MulTa-HDC outperforms other state-of-the-art compressed HD models, including SparseHD and CompHD, by up to 8.23% in terms of classification accuracy. © 1968-2012 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85104648560&doi=10.1109%2fTC.2021.3073409&partnerID=40&md5=b0a1c3a9128b0cf5e9ad428ad1004150 https://scholars.lib.ntu.edu.tw/handle/123456789/611190 |
ISSN: | 00189340 | 其他識別: | ITCOB | DOI: | 10.1109/TC.2021.3073409 | SDG/關鍵字: | Associative processing; Classification (of information); Economic and social effects; Internet of things; Learning systems; Linearization; Associative memory; Classification accuracy; Hybrid framework; Internet of thing (IOT); Memory overheads; Memory retrieval; Performance degradation; State of the art; Multi-task learning |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。