Login / Signup

TrainWare: A Memory Optimized Weight Update Architecture for On-Device Convolutional Neural Network Training.

Seungkyu ChoiJaehyeong SimMyeonggu KangLee-Sup Kim
Published in: ISLPED (2018)
Keyphrases
  • neural network training
  • weight update
  • neural network
  • network architecture
  • training algorithm
  • back propagation
  • gradient vector
  • spiking neural networks
  • online training
  • machine learning
  • data fusion
  • learning rate