LE QUY DON
Technical University
VietnameseClear Cookie - decide language by browser settings

Efficient Low-Latency Dynamic Licensing for Deep Neural Network Deployment on Edge Devices

Pham, T.V. and Tran, N.N.Q. and Pham, H.M. and Nguyen, T.M. and Ta Minh, T. (2020) Efficient Low-Latency Dynamic Licensing for Deep Neural Network Deployment on Edge Devices. In: 3rd International Conference on Computational Intelligence and Intelligent Systems, CIIS 2020, 13 November 2020 through 15 November 2020.

Text
Efficient Low-Latency Dynamic Licensing for Deep Neural Network Deployment on Edge Devices.pdf

Download (845kB) | Preview

Abstract

Along with the rapid development in the field of artificial intelligence (AI), especially deep learning, deep neural network (DNN) applications are becoming more and more popular in reality. To be able to withstand the heavy load from mainstream users, deployment techniques are essential in bringing neural network models from research to production. Among the two popular computing topologies for deploying neural network models in production are cloud-computing and edge-computing. Recent advances in communication technologies, along with the great increase in the number of mobile devices, has made edge-computing gradually become an inevitable trend. In this paper, we propose an architecture to solve deploying and processing deep neural networks on edge-devices by leveraging their synergy with the cloud and the access-control mechanisms of the database. Adopting this architecture allows low-latency DNN model updates on devices. At the same time, with only one model deployed, we can easily make different versions of it by setting access permissions on the model weights. This method allows for dynamic model licensing, which benefits commercial applications. © 2020 ACM.

Item Type: Conference or Workshop Item (Paper)
Divisions: Faculties > Faculty of Information Technology
Identification Number: 10.1145/3440840.3440860
Uncontrolled Keywords: Access control; Deep learning; Deep neural networks; Edge computing; Intelligent computing; Memory architecture; Network architecture; Access control mechanism; Access permissions; Commercial applications; Communication technologies; Computing topology; Inevitable trends; Model weights; Neural network model; Neural networks
Additional Information: Conference code: 167083. Language of original document: English. All Open Access, Green.
URI: http://eprints.lqdtu.edu.vn/id/eprint/8867

Actions (login required)

View Item
View Item