A Computing-in-Memory-Based One-Class Hyperdimensional Computing Model for Outlier Detection
IEEE Transactions on Computers · 2024-06 · 73 (6) · 1559-1574
DOI: 10.1109/tc.2024.3371782 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Computers, 2024-06. Verfasst von Ruixuan Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: U.S. NSF, ACCESS – AI Chip Center for Emerging Smart Systems, sponsored by InnoHK.
Abstract (Originalsprache)
In this work, we present ODHD , an algorithm for outlier detection based on hyperdimensional computing (HDC), a non-classical learning paradigm. Along with the HDC-based algorithm, we propose IM-ODHD , a computing-in-memory (CiM) implementation based on hardware/software (HW/SW) codesign for improved latency and energy efficiency. The training and testing phases of ODHD may be performed with conventional CPU/GPU hardware or our IM-ODHD , SRAM-based CiM architecture using the proposed HW/SW codesign techniques. We evaluate the performance of ODHD on six datasets from different application domains using three metrics, namely accuracy, F1 score, and ROC-AUC, and compare it with multiple baseline methods such as OCSVM, isolation forest, and autoencoder. The experimental results indicate that ODHD outperforms all the baseline methods in terms of these three metrics on every dataset for both CPU/GPU and CiM implementations. Furthermore, we perform an extensive design space exploration to demonstrate the tradeoff between delay, energy efficiency, and performance of ODHD . We demonstrate that the HW/SW codesign implementation of the outlier detection on IM-ODHD is able to outperform the GPU-based implementation of ODHD by at least 331.5 $\times$ × /889 $\times$ × in terms of training/testing latency (and on average 14.0 $\times$ × /36.9 $\times$ × in terms of training/testing energy consumption).
Förderung
- U.S. NSF
- ACCESS – AI Chip Center for Emerging Smart Systems, sponsored by InnoHK
Zitieren
APA
Wang, R., Moon, S. H., Hu, X. S., Jiao, X., & Reis, D. (2024). A Computing-in-Memory-Based One-Class Hyperdimensional Computing Model for Outlier Detection. IEEE Transactions on Computers, 73(6), 1559-1574. https://doi.org/10.1109/tc.2024.3371782
Vancouver
Wang R, Moon SH, Hu XS, Jiao X, Reis D. A Computing-in-Memory-Based One-Class Hyperdimensional Computing Model for Outlier Detection. IEEE Transactions on Computers. 2024;73(6):1559-1574. doi:10.1109/tc.2024.3371782
BibTeX
@article{Wang2024,
author = {Wang, Ruixuan and Moon, Sabrina Hassan and Hu, Xiaobo Sharon and Jiao, Xun and Reis, Dayane},
title = {A Computing-in-Memory-Based One-Class Hyperdimensional Computing Model for Outlier Detection},
journal = {IEEE Transactions on Computers},
year = {2024},
volume = {73},
number = {6},
pages = {1559--1574},
doi = {10.1109/tc.2024.3371782}
}
EUVIMED