MulTa-HDC: A Multi-Task Learning Framework For Hyperdimensional Computing
| العنوان: | MulTa-HDC: A Multi-Task Learning Framework For Hyperdimensional Computing |
|---|---|
| المؤلفون: | An-Yeu Andy Wu, En-Jui Chang, Yu-Chuan Chuang, Cheng-Yang Chang |
| المصدر: | IEEE Transactions on Computers. 70:1269-1284 |
| بيانات النشر: | Institute of Electrical and Electronics Engineers (IEEE), 2021. |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | Edge device, Computer science, business.industry, Multi-task learning, Content-addressable memory, Machine learning, computer.software_genre, Theoretical Computer Science, Task (computing), Memory management, Computational Theory and Mathematics, Hardware and Architecture, Overhead (computing), Artificial intelligence, business, computer, Software, Edge computing, MNIST database |
| الوصف: | 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 Mul ti- Ta sking 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. |
| تدمد: | 2326-3814 0018-9340 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_________::1d1dd2ab1f2116952e85208fadde199a https://doi.org/10.1109/tc.2021.3073409 |
| رقم الأكسشن: | edsair.doi...........1d1dd2ab1f2116952e85208fadde199a |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 23263814 00189340 |
|---|