Hyperdimensional Computing with Learnable Projection for User Adaptation Framework - Artificial Intelligence Applications and Innovations
Conference Papers Year : 2021

Hyperdimensional Computing with Learnable Projection for User Adaptation Framework

Yu-Ren Hsiao
  • Function : Author
  • PersonId : 1105455
Yu-Chuan Chuang
  • Function : Author
  • PersonId : 1105414
Cheng-Yang Chang
  • Function : Author
  • PersonId : 1105413
An-Yeu (andy) Wu
  • Function : Author
  • PersonId : 1105411

Abstract

Brain-inspired Hyperdimensional Computing (HDC), a machine learning (ML) model featuring high energy efficiency and fast adaptability, provides a promising solution to many real-world tasks on resource-limited devices. This paper introduces an HDC-based user adaptation framework, which requires efficient fine-tuning of HDC models to boost accuracy. Specifically, we propose two techniques for HDC, including the learnable projection and the fusion mechanism for the Associative Memory (AM). Compared with the user adaptation framework based on the original HDC, our proposed framework shows 4.8% and 3.5% of accuracy improvements on two benchmark datasets, including the ISOLET dataset and the UCIHAR dataset, respectively.
Fichier principal
Vignette du fichier
509922_1_En_35_Chapter.pdf (935.32 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03287688 , version 1 (15-07-2021)

Licence

Identifiers

Cite

Yu-Ren Hsiao, Yu-Chuan Chuang, Cheng-Yang Chang, An-Yeu (andy) Wu. Hyperdimensional Computing with Learnable Projection for User Adaptation Framework. 17th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2021, Hersonissos, Crete, Greece. pp.436-447, ⟨10.1007/978-3-030-79150-6_35⟩. ⟨hal-03287688⟩
115 View
64 Download

Altmetric

Share

More