Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing

Пограничный интеллект: прокладывая последний участок пути для искусственного интеллекта с помощью периферийных вычислений
Xu Chen, Zhi Zhou, En Li, Liekang Zeng, Ke Luo, Junshan Zhang
2019-06-12

Internet of Thingsdeep learningedge AIedge computingedge intelligence
With the breakthroughs in deep learning, the recent years have witnessed a booming of artificial intelligence (AI) applications and services, spanning from personal assistant to recommendation systems to video/audio surveillance. More recently, with the proliferation of mobile computing and Internet of Things (IoT), billions of mobile and IoT devices are connected to the Internet, generating zillions bytes of data at the network edge. Driving by this trend, there is an urgent need to push the AI frontiers to the network edge so as to fully unleash the potential of the edge big data. To meet this demand, edge computing, an emerging paradigm that pushes computing tasks and services from the network core to the network edge, has been widely recognized as a promising solution. The resulted new interdiscipline, edge AI or edge intelligence (EI), is beginning to receive a tremendous amount of interest. However, research on EI is still in its infancy stage, and a dedicated venue for exchanging the recent advances of EI is highly desired by both the computer system and AI communities. To this end, we conduct a comprehensive survey of the recent research efforts on EI. Specifically, we first review the background and motivation for AI running at the network edge. We then provide an overview of the overarching architectures, frameworks, and emerging key technologies for deep learning model toward training/inference at the network edge. Finally, we discuss future research opportunities on EI. We believe that this survey will elicit escalating attentions, stimulate fruitful discussions, and inspire further research ideas on EI.
1
Edge intelligence combines AI with edge computing to process growing mobile and IoT data closer to where it is generated.
2
Edge intelligence research is characterized as being in its infancy, motivating dedicated cross-disciplinary study spanning computer systems and artificial intelligence.
3
Pushing AI tasks toward the network edge is presented as a way to reduce dependence on centralized network-core computing and exploit edge-generated big data.
4
The paper identifies future research opportunities intended to guide further development of edge intelligence.
5
The survey reviews architectures, frameworks, and key technologies supporting deep-learning training and inference at the network edge.

Edge intelligence (edge AI) — deployment of artificial intelligence (deep learning) capabilities at the network edge (edge computing devices and IoT/mobile devices)

architectures, frameworks, and key technologies for deploying deep-learning training and inference at the network edge

Publication Details
Publication Date
2019-06-12
Journal
Publisher
ISSN
Cited by
3152
Access Type
Author Information
Authors
Xu Chen
Zhi Zhou
En Li
Liekang Zeng
Ke Luo
Junshan Zhang
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%