https://scholars.lib.ntu.edu.tw/handle/123456789/611198
標題: | PQ-HDC: Projection-Based Quantization Scheme for Flexible and Efficient Hyperdimensional Computing | 作者: | AN-YEU(ANDY) WU | 關鍵字: | Brain-inspired computing; Dynamic model; Energy efficiency; Hyperdimensional Computing | 公開日期: | 2021 | 卷: | 627 | 起(迄)頁: | 425-435 | 來源出版物: | IFIP Advances in Information and Communication Technology | 摘要: | Brain-inspired Hyperdimensional (HD) computing is an emerging technique for low-power/energy designs in many machine learning tasks. Recent works further exploit the low-cost quantized (bipolarized or ternarized) HD model and report dramatic improvements in energy efficiency. However, the quantization loss of HD models leads to a severe drop in classification accuracy. This paper proposes a projection-based quantization framework for HD computing (PQ-HDC) to achieve a flexible and efficient trade-off between accuracy and efficiency. While previous works exploit thresholding-quantization schemes, the proposed PQ-HDC progressively reduces quantization loss using a linear combination of bipolarized HD models. Furthermore, PQ-HDC allows quantization with flexible bit-width while preserving the computational efficiency of the Hamming distance computation. Experimental results on the benchmark dataset demonstrate that PQ-HDC achieves a 2.82% improvement in accuracy over the state-of-the-art method. © 2021, IFIP International Federation for Information Processing. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85111889696&doi=10.1007%2f978-3-030-79150-6_34&partnerID=40&md5=7dd0235e87485e9443952717e42ab923 https://scholars.lib.ntu.edu.tw/handle/123456789/611198 |
ISBN: | 9.78303E+12 | ISSN: | 18684238 | DOI: | 10.1007/978-3-030-79150-6_34 | SDG/關鍵字: | Computational efficiency; Economic and social effects; Energy efficiency; Hamming distance; Benchmark datasets; Classification accuracy; Hamming distance computation; Linear combinations; Low power/energy; Quantization loss; Quantization schemes; State-of-the-art methods; Artificial intelligence |
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。