Skip to Main content Skip to Navigation
Conference papers

PQ-HDC: Projection-Based Quantization Scheme for Flexible and Efficient Hyperdimensional Computing

Abstract : 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.
Document type :
Conference papers
Complete list of metadata
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Thursday, July 15, 2021 - 6:10:08 PM
Last modification on : Thursday, July 15, 2021 - 6:31:50 PM
Long-term archiving on: : Saturday, October 16, 2021 - 7:04:01 PM


 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : 2024-01-01

Please log in to resquest access to the document


Distributed under a Creative Commons Attribution 4.0 International License



Chi-Tse Huang, Cheng-yang Chang, yu-Chuan Chuang, An-yeu (andy) Wu. PQ-HDC: Projection-Based Quantization Scheme for Flexible and Efficient Hyperdimensional Computing. 17th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2021, Hersonissos, Crete, Greece. pp.425-435, ⟨10.1007/978-3-030-79150-6_34⟩. ⟨hal-03287667⟩



Record views