Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing Zhi Zhou, Xu Chen, En Li, Liekang Zeng, Ke Luo, Junshan Zhang Abstract—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 billions 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 inter-discipline, edge AI or edge intelligence, is beginning to receive a tremendous amount of interest. However, research on edge intelligence is still in its infancy stage, and a dedicated venue for exchanging the recent advances of edge intelligence is highly desired by both the computer system and artificial intelligence communities. To this end, we conduct a comprehensive survey of the recent research efforts on edge intelligence. Specifically, we first review the background and motivation for artificial intelligence running at the network edge. We then provide an overview of the overarching architectures, frameworks and emerging key technologies for deep learning model towards training/inference at the network edge. Finally, we discuss future research opportunities on edge intelligence. We believe that this survey will elicit escalating attentions, stimulate fruitful discussions and inspire further research ideas on edge intelligence. Edge intelligence is the integration of edge computing and AI, aiming to bring AI capabilities closer to the data source at the network edge. This survey provides a comprehensive overview of the recent research efforts in edge intelligence, including the background and motivation for AI at the network edge, the architectures and frameworks for deep learning model training and inference at the network edge, and future research opportunities. Edge intelligence has gained significant attention from both industry and academia, with major enterprises such as Google, Microsoft, Intel, and IBM investing in edge computing to advance AI applications. However, research on edge intelligence is still in its early stages, and there is a need for a dedicated venue to summarize, discuss, and disseminate recent advances in edge intelligence. This survey aims to fill this gap by providing a comprehensive and concrete review of the recent research efforts in edge intelligence. The paper is organized as follows: Section II gives an overview of the basic concepts of artificial intelligence, with a focus on deep learning. Section III discusses the motivation, definition, and rating of edge intelligence. Section IV reviews the architectures, enabling techniques, systems, and frameworks for training edge intelligence models. Section V reviews the architectures, enabling techniques, systems, and frameworks for edge intelligence model inference. Section VI discusses future directions andEdge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing Zhi Zhou, Xu Chen, En Li, Liekang Zeng, Ke Luo, Junshan Zhang Abstract—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 billions 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 inter-discipline, edge AI or edge intelligence, is beginning to receive a tremendous amount of interest. However, research on edge intelligence is still in its infancy stage, and a dedicated venue for exchanging the recent advances of edge intelligence is highly desired by both the computer system and artificial intelligence communities. To this end, we conduct a comprehensive survey of the recent research efforts on edge intelligence. Specifically, we first review the background and motivation for artificial intelligence running at the network edge. We then provide an overview of the overarching architectures, frameworks and emerging key technologies for deep learning model towards training/inference at the network edge. Finally, we discuss future research opportunities on edge intelligence. We believe that this survey will elicit escalating attentions, stimulate fruitful discussions and inspire further research ideas on edge intelligence. Edge intelligence is the integration of edge computing and AI, aiming to bring AI capabilities closer to the data source at the network edge. This survey provides a comprehensive overview of the recent research efforts in edge intelligence, including the background and motivation for AI at the network edge, the architectures and frameworks for deep learning model training and inference at the network edge, and future research opportunities. Edge intelligence has gained significant attention from both industry and academia, with major enterprises such as Google, Microsoft, Intel, and IBM investing in edge computing to advance AI applications. However, research on edge intelligence is still in its early stages, and there is a need for a dedicated venue to summarize, discuss, and disseminate recent advances in edge intelligence. This survey aims to fill this gap by providing a comprehensive and concrete review of the recent research efforts in edge intelligence. The paper is organized as follows: Section II gives an overview of the basic concepts of artificial intelligence, with a focus on deep learning. Section III discusses the motivation, definition, and rating of edge intelligence. Section IV reviews the architectures, enabling techniques, systems, and frameworks for training edge intelligence models. Section V reviews the architectures, enabling techniques, systems, and frameworks for edge intelligence model inference. Section VI discusses future directions and