Login / Signup

Deep compressive offloading: speeding up neural network inference by trading edge computation for network latency.

Shuochao YaoJinyang LiDongxin LiuTianshi WangShengzhong LiuHuajie ShaoTarek F. Abdelzaher
Published in: SenSys (2020)
Keyphrases
  • network latency
  • neural network
  • response time
  • memory requirements
  • distributed network
  • network bandwidth
  • image retrieval