A Dynamic Deep Neural Network Design for Efficient Workload Allocation in Edge Computing
By Chi Lo, Yu-Yi Su, Chun-Yi Lee, Shih-Chieh Chang. 2017
44 citations recorded by the source corpus.
Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, ML Systems & Hardware
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Networks and Communications
- Michele Scarpiniti
- Marco Levorato
- Enzo Baccarelli
- Simone Scardapane
- Bashir I. Morshed
- Syed Kamrul Islam
- Jianlin Cheng
- Md Maruf Hossain Shuvo
In Computer Vision and Pattern Recognition
- Michele Scarpiniti
- Enzo Baccarelli
- Simone Scardapane
- Aurelio Uncini
- Francesco Restuccia
- Marco Levorato
- Bashir I. Morshed
- Syed Kamrul Islam
In Electrical and Electronic Engineering
- Francesco Restuccia
- Marco Levorato
- Simone Scardapane
- Bashir I. Morshed
- Syed Kamrul Islam
- Jianlin Cheng
- Md Maruf Hossain Shuvo
- Yoshitomo Matsubara
Citations in the corpus
- Why Should We Add Early Exits to Neural Networks? (2020, background): “In these works, it is common to design systems in which separate neural networks, of different complexities, can run on the different tiers or on different computational units [ 44, 50 ] .”
- Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges (2021, methodology): “Using the concept of EE, Lo et al. [87] proposes two different methods: (i) authentic operation, and (ii) dynamic network sizing.”
- Efficient Acceleration of Deep Learning Inference on Resource-Constrained Edge Devices: A Review (2023, background): “An authentic operation (AO) unit is added to BranchyNet in [216] to determine whether the input is to be passed to the edge server or cloud based on the confidence score.”
- Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing (2019, unknown): “[90] propose adding an authentic operation (AO) unit to the basic BranchyNet model.”