Login / Signup

WRA: A 2.2-to-6.3 TOPS Highly Unified Dynamically Reconfigurable Accelerator Using a Novel Winograd Decomposition Algorithm for Convolutional Neural Networks.

Chen YangYizhou WangXiaoli WangLi Geng
Published in: IEEE Trans. Circuits Syst. I Regul. Pap. (2019)
Keyphrases
  • decomposition algorithm
  • convolutional neural networks
  • decomposition method
  • working set
  • convolutional network
  • equality constraints
  • working set selection
  • training data
  • multiresolution