Hyperdimensional Computing for Robust and Efficient Unsupervised Learning

Sanggeon Yun, Hamza Errahmouni Barkam, Paul R. Genssler, Hugo Latapie, Hussam Amrouch, Mohsen Imani

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Clustering has emerged as a critical tool in diverse fields. Nevertheless, its high computational cost has been a persistent challenge, particularly for large-scale datasets. To address this, various compute-in-memory (CiM) approaches have been proposed, including the use of Ferroelectric FET (FeFET) technology due to its ultra-efficient and compact CiM architecture. However, non-idealities resulting from cell thickness and device temperature have impeded the scaling of FeFETs and thus hindered their potential to be used for clustering. In light of this, we propose a Hyper-Dimensional Computing (HDC) framework specifically for FeFET technology in the context of clustering. Our approach involves a cross-layer FeFET reliability model that captures the effects of scaling on multi-bit FeFETs, taking into account the impact of process variation and inherent stochasticity. We use two models in our HDC framework, a full-precision, ideal model for training, and a quantized error-impacted version for validation and inference. This iterative adaptation strategy helps to overcome the challenges associated with the non-idealities of FeFET technology. Our results demonstrate the proposed HDC framework performs better than traditional algorithms such as k-means and BIRCH. Moreover, our model can function as its ideal counterpart without noise, proving its potential to scale FeFET technology for clustering applications.

Original languageEnglish
Title of host publicationConference Record of the 57th Asilomar Conference on Signals, Systems and Computers, ACSSC 2023
EditorsMichael B. Matthews
PublisherIEEE Computer Society
Pages281-288
Number of pages8
ISBN (Electronic)9798350325744
DOIs
StatePublished - 2023
Event57th Asilomar Conference on Signals, Systems and Computers, ACSSC 2023 - Pacific Grove, United States
Duration: 29 Oct 20231 Nov 2023

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
ISSN (Print)1058-6393

Conference

Conference57th Asilomar Conference on Signals, Systems and Computers, ACSSC 2023
Country/TerritoryUnited States
CityPacific Grove
Period29/10/231/11/23

Keywords

  • FeFET
  • clustering
  • computing in memory
  • data science
  • hyperdimensional computing

Fingerprint

Dive into the research topics of 'Hyperdimensional Computing for Robust and Efficient Unsupervised Learning'. Together they form a unique fingerprint.

Cite this