1 Ocak 2021 Konferans bildirisi Açık Erişim

Nojehdeh, Mohammadreza Esmali; Parvin, Sajjad; Altun, Mustafa

JSON-LD (schema.org)

{
  "@context": "https://schema.org/", 
  "@id": 234352, 
  "@type": "ScholarlyArticle", 
  "creator": [
    {
      "@type": "Person", 
      "affiliation": "Istanbul Tech Univ, Dept Elect & Commun Engn, TR-34469 Istanbul, Turkey", 
      "name": "Nojehdeh, Mohammadreza Esmali"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Tech Univ, Dept Elect & Commun Engn, TR-34469 Istanbul, Turkey", 
      "name": "Parvin, Sajjad"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Istanbul Tech Univ, Dept Elect & Commun Engn, TR-34469 Istanbul, Turkey", 
      "name": "Altun, Mustafa"
    }
  ], 
  "datePublished": "2021-01-01", 
  "description": "In this paper, we propose an efficient method to realize a convolution layer of the convolution neural networks (CNNs). Inspired by the hilly-connected neural network architecture, we introduce an efficient computation approach to implement convolution operations. Also, to reduce hardware complexity, we implement convolutional layers under the time-multiplexed architecture where computing resources are re-used in the multiply-accumulate (MAC) blocks. A comprehensive evaluation of convolution layers shows using our proposed method when compared to the conventional MAC-based method results up to 97% and 50% reduction in dissipated power and computation time, respectively.", 
  "headline": "Efficient Hardware Implementation of Convolution Layers Using Multiply-Accumulate Blocks", 
  "identifier": 234352, 
  "image": "https://aperta.ulakbim.gov.tr/static/img/logo/aperta_logo_with_icon.svg", 
  "license": "http://www.opendefinition.org/licenses/cc-by", 
  "name": "Efficient Hardware Implementation of Convolution Layers Using Multiply-Accumulate Blocks", 
  "url": "https://aperta.ulakbim.gov.tr/record/234352"
}