Registered
METHOD AND APPARATUS FOR PARTITIONING DEEP NEURAL NETWORKS
- Inventors
-
Lee Chang Sik, Hong Sung Back, Seungwoo Hong, Ryu Ho Yong
- Application No.
-
16830253 (2020.03.25)
- Publication No.
-
20200311546 (2020.10.01)
- Registration No.
- 11521066 (2022.12.06)
- Country
- UNITED STATES
- Project Code
-
19HH2100, A Development for Intellectualized Edge Networking based on AI,
Tae Yeon Kim
- Abstract
- A processor partitions a deep neural network having a plurality of exit points and at least one partition point in a branch corresponding to each of the exit points, for distributed processing in an edge device and a cloud. The processor sets environmental variables and training variables for training, selects an action to move at least one of an exit point and a partition point from a combination of the exit point and the partition point corresponding to a current state, performs the training by accumulating experience data using a reward according to the selected action and then moves to a next state, and outputs a combination of an optimal exit point and a partition point as a result of the training.
- KSP Keywords
- Current state, Deep neural network(DNN), Edge devices, Partition point, distributed processing, environmental variables, neural network
- Family
-