Task-Projected Hyperdimensional Computing for Multi-Task Learning - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2020

Task-Projected Hyperdimensional Computing for Multi-Task Learning

Andy Wu
  • Function : Author
  • PersonId : 1105411

Abstract

Brain-inspired Hyperdimensional (HD) computing is an emerging technique for cognitive tasks in the field of low-power design. As an energyefficient and fast learning computational paradigm, HD computing has shown great success in many real-world applications. However, an HD model incrementally trained on multiple tasks suffers from the negative impacts of catastrophic forgetting. The model forgets the knowledge learned from previous tasks and only focuses on the current one. To the best of our knowledge, no study has been conducted to investigate the feasibility of applying multi-task learning to HD computing. In this paper, we propose Task-Projected Hyperdimensional Computing (TP-HDC) to make the HD model simultaneously support multiple tasks by exploiting the redundant dimensionality in the hyperspace. To mitigate the interferences between different tasks, we project each task into a separate subspace for learning. Compared with the baseline method, our approach efficiently utilizes the unused capacity in the hyperspace and shows a 12.8% improvement in averaged accuracy with negligible memory overhead.
Fichier principal
Vignette du fichier
497040_1_En_21_Chapter.pdf (990.77 Ko) Télécharger le fichier
Origin Explicit agreement for this submission
Licence

Dates and versions

hal-04051018 , version 1 (29-03-2023)

Licence

Identifiers

  • HAL Id : hal-04051018 , version 1

Cite

Cheng-Yang Chang, Yu-Chuan Chuang, Andy Wu. Task-Projected Hyperdimensional Computing for Multi-Task Learning. 16th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2020, Neos Marmaras, Greece. pp.241-254. ⟨hal-04051018⟩
22 View
14 Download

Share

More