Sponsor:
Latency and energy consumption of DNN queries can be significantly improved by splitting the workload between the mobile and cloud. Real-time scheduling of computations between the mobile and cloud and efficient feature communication are studied in this project.Related work:
- A. E. Eshratifar, A. Esmaili, M. Pedram, Towards Collaborative Intelligence Friendly Architectures for Deep Learning, to appear in ISQED 2019.
- A. E. Eshratifar, M. S. Abrishami, and M. Pedram, JointDNN: an efficient training and inference engine for intelligent mobile cloud computing services, arXiv preprint, Jan. 2018.
- E. Eshratifar and M. Pedram,Energy and Performance Efficient Computation Offloading for Deep Neural Networks in a Mobile Cloud Computing Environment, Proc. of ACM Great Lakes Symp. on VLSI, May 2018.