• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Convolution Neural Network Development Support System using Approximation Methods to Evaluate Inference Accuracy and Memory Usage in an Embedded System.

Toki MatsumotoYukikazu NakamotoRyota YamamotoShinya HondaKazutoshi Wakabayashi
Published in: SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI (2019)
Keyphrases
  • memory usage
  • approximation methods
  • neural network
  • memory footprint
  • artificial neural networks
  • memory requirements
  • computational complexity
  • probabilistic model
  • back propagation
  • radial basis function