Journal article Open Access

Energy Efficient In-Memory Hyperdimensional Encoding for Spatio-Temporal Signal Processing

Karunaratne, Geethan; Le Gallo, Manuel; Hersche, Michael; Cherubini, Giovanni; Benini, Luca; Sebastian, Abu; Rahimi, Abbas


JSON-LD (schema.org) Export

{
  "description": "<p>The emerging brain-inspired computing paradigm known as hyperdimensional computing (HDC) has been proven to provide a lightweight learning framework for various cognitive tasks compared to the widely used deep learning-based approaches. Spatio-temporal (ST) signal processing, which encompasses biosignals such as electromyography (EMG) and electroencephalography (EEG), is one family of applications that could benefit from an HDC-based learning framework. At the core of HDC lie manipulations and comparisons of large bit patterns, which are inherently ill-suited to conventional computing platforms based on the von-Neumann architecture. In this work, we propose an architecture for ST signal processing within the HDC framework using predominantly in-memory compute arrays. In particular, we introduce a methodology for the in-memory hyperdimensional encoding of ST data to be used together with an in-memory associative search module. We show that the in-memory HDC encoder for ST signals offers at least 1.80&times; energy efficiency gains, 3.36&times; area gains, as well as 9.74&times; throughput gains compared with a dedicated digital hardware implementation. At the same time it achieves a peak classification accuracy within 0.04% of that of the baseline HDC framework.</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "IBM Research - Zurich", 
      "@type": "Person", 
      "name": "Karunaratne, Geethan"
    }, 
    {
      "affiliation": "IBM Research - Zurich", 
      "@type": "Person", 
      "name": "Le Gallo, Manuel"
    }, 
    {
      "affiliation": "IBM Research - Zurich", 
      "@type": "Person", 
      "name": "Hersche, Michael"
    }, 
    {
      "affiliation": "IBM Research - Zurich", 
      "@type": "Person", 
      "name": "Cherubini, Giovanni"
    }, 
    {
      "affiliation": "ETH Zurich", 
      "@type": "Person", 
      "name": "Benini, Luca"
    }, 
    {
      "affiliation": "IBM Research - Zurich", 
      "@type": "Person", 
      "name": "Sebastian, Abu"
    }, 
    {
      "affiliation": "IBM Research - Zurich", 
      "@type": "Person", 
      "name": "Rahimi, Abbas"
    }
  ], 
  "headline": "Energy Efficient In-Memory Hyperdimensional Encoding for Spatio-Temporal Signal Processing", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2021-03-25", 
  "url": "https://zenodo.org/record/5301648", 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.1109/TCSII.2021.3068126", 
  "@id": "https://doi.org/10.1109/TCSII.2021.3068126", 
  "@type": "ScholarlyArticle", 
  "name": "Energy Efficient In-Memory Hyperdimensional Encoding for Spatio-Temporal Signal Processing"
}
6
8
views
downloads
Views 6
Downloads 8
Data volume 10.9 MB
Unique views 5
Unique downloads 8

Share

Cite as