Journal article Open Access

Compressed sensing with approximate message passing using in-memory computing

Le Gallo, Manuel; Sebastian, Abu; Cherubini, Giovanni; Giefers, Heiner; Eleftheriou, Evangelos


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/90ec87b1-e208-449a-8e95-ff396ceef2aa/LeGallo18.pdf"
      }, 
      "checksum": "md5:77eb782ef6baab0f8b8ae06eb59a73fa", 
      "bucket": "90ec87b1-e208-449a-8e95-ff396ceef2aa", 
      "key": "LeGallo18.pdf", 
      "type": "pdf", 
      "size": 586406
    }
  ], 
  "owners": [
    55780
  ], 
  "doi": "10.1109/TED.2018.2865352", 
  "stats": {
    "version_unique_downloads": 55.0, 
    "unique_views": 22.0, 
    "views": 23.0, 
    "version_views": 23.0, 
    "unique_downloads": 55.0, 
    "version_unique_views": 22.0, 
    "volume": 32838736.0, 
    "version_downloads": 56.0, 
    "downloads": 56.0, 
    "version_volume": 32838736.0
  }, 
  "links": {
    "doi": "https://doi.org/10.1109/TED.2018.2865352", 
    "latest_html": "https://zenodo.org/record/3249877", 
    "bucket": "https://zenodo.org/api/files/90ec87b1-e208-449a-8e95-ff396ceef2aa", 
    "badge": "https://zenodo.org/badge/doi/10.1109/TED.2018.2865352.svg", 
    "html": "https://zenodo.org/record/3249877", 
    "latest": "https://zenodo.org/api/records/3249877"
  }, 
  "created": "2019-06-19T08:54:34.182222+00:00", 
  "updated": "2020-01-20T16:10:34.966723+00:00", 
  "conceptrecid": "3249876", 
  "revision": 5, 
  "id": 3249877, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.1109/TED.2018.2865352", 
    "description": "<p>In-memory computing is a promising non-von Neumann approach where certain computational tasks are performed within resistive memory units by exploiting their physical attributes. In this paper, we propose a new method for fast and robust compressed sensing of sparse signals with approximate message passing recovery using in-memory computing. The measurement matrix for compressed sensing is encoded in the conductance states of resistive memory devices organized in a crossbar array. This way, the matrix-vector multiplications associated with both the compression and recovery tasks can be performed by the same crossbar array without intermediate data movements at potential O(1) time complexity. For a signal of size N, the proposed method achieves a potential O(N)-fold recovery complexity reduction compared with a standard software approach. We show the array-level robustness of the scheme through large-scale experimental demonstrations using more than 256k phase-change memory devices.</p>", 
    "license": {
      "id": "CC-BY-NC-ND-4.0"
    }, 
    "title": "Compressed sensing with approximate message passing using in-memory computing", 
    "journal": {
      "volume": "65", 
      "issue": "10", 
      "pages": "4304-4312", 
      "title": "IEEE Transactions on Electron Devices"
    }, 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3249876"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "3249877"
          }
        }
      ]
    }, 
    "grants": [
      {
        "code": "682675", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::682675"
        }, 
        "title": "PROJECTED MEMRISTOR: A nanoscale device for cognitive computing", 
        "acronym": "PROJESTOR", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }, 
      {
        "code": "780215", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::780215"
        }, 
        "title": "Computation-in-memory architecture based on resistive devices", 
        "acronym": "MNEMOSENE", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "keywords": [
      "Approximate message passing", 
      "Compressed sensing", 
      "In-memory computing", 
      "Phase-change memory"
    ], 
    "publication_date": "2018-08-29", 
    "creators": [
      {
        "affiliation": "IBM Research - Zurich, 8803 R\u00fcschlikon, Switzerland", 
        "name": "Le Gallo, Manuel"
      }, 
      {
        "affiliation": "IBM Research - Zurich, 8803 R\u00fcschlikon, Switzerland", 
        "name": "Sebastian, Abu"
      }, 
      {
        "affiliation": "IBM Research - Zurich, 8803 R\u00fcschlikon, Switzerland", 
        "name": "Cherubini, Giovanni"
      }, 
      {
        "name": "Giefers, Heiner"
      }, 
      {
        "name": "Eleftheriou, Evangelos"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "subtype": "article", 
      "type": "publication", 
      "title": "Journal article"
    }
  }
}
23
56
views
downloads
Views 23
Downloads 56
Data volume 32.8 MB
Unique views 22
Unique downloads 55

Share

Cite as