1 Ocak 2021 Konferans bildirisi Açık Erişim

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

Citation Style Language JSON

{
  "DOI": "10.1109/ISVLSI51109.2021.00079", 
  "abstract": "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.", 
  "author": [
    {
      "family": "Nojehdeh", 
      "given": " Mohammadreza Esmali"
    }, 
    {
      "family": "Parvin", 
      "given": " Sajjad"
    }, 
    {
      "family": "Altun", 
      "given": " Mustafa"
    }
  ], 
  "id": "234352", 
  "issued": {
    "date-parts": [
      [
        2021, 
        1, 
        1
      ]
    ]
  }, 
  "title": "Efficient Hardware Implementation of Convolution Layers Using Multiply-Accumulate Blocks", 
  "type": "paper-conference"
}