arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.12165cs.LGcs.NI
收藏

边缘设备上深度神经网络部署的高效低延迟动态许可

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

R&D Lab, Sun* Inc.(Sun*公司研发实验室);Le Quy Don Technical University(黎贵惇理工大学)

Toan Pham Van, Ngoc N. Tran, Hoang Pham Minh, Tam Nguyen Minh, Thanh Ta Minh

摘要:

伴随着人工智能特别是深度学习领域的快速发展,深度神经网络应用在现实中越来越普及。为了能够承受来自主流用户的沉重负载,部署技术对于将神经网络模型从研究带到生产中至关重要。在生产中部署神经网络模型的两种流行的计算拓扑是云计算和边缘计算。近年来通信技术的进步,以及移动设备数量的大幅增加,使得边缘计算逐渐成为一种必然趋势。在本文中,我们提出了一种架构,通过利用它们与云和数据库访问控制机制的协同作用,解决在边缘设备上部署和处理深度神经网络的问题。采用这种架构允许设备上的低延迟DNN模型更新。同时,由于只部署了一个模型,我们可以通过设置模型权重的访问权限来轻松地创建不同版本的模型。这种方法允许动态模型许可,这有利于商业应用。

英文摘要:

Along with the rapid development in the field of artificial intelligence, especially deep learning, deep neural network 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑