Recently, artificial intelligence (AI) is undergoing a sustained success renaissance as it can substantially improve networks' cognitive performance and intelligence, thereby contributing to fully unleashing the potential of big data. Pushing the AI frontiers to the network edge in this context and trends has given rise to an emerging interdiscipline, namely, edge intelligence (EI). Indeed, EI can sink the cloud's processing capabilities to the edge side, and provide real-time response while enabling more intelligent services with high performance. However, the successful realization of EI is still in its infancy. Thus, this article aims to provide a comprehensive study of this young field from a broader perspective. We first discuss the prior knowledge based on which we take a holistic overview of EI, including its key concepts, advantages, and development trend. Then we highlight the collaboration modes in EI, and discuss two typical case categories. Subsequently, the entire processes of model training and inference in EI are elaborated. Finally, we discuss a typical application scenario and its specific embodiment of EI and strive to shed light on some potential challenges, which may facilitate the transformation of EI from theory to practice.

中文翻译：

---

智能赋能的移动边缘计算：框架、问题、实施和展望


近年来，人工智能（AI）正在持续成功复兴，它可以大幅提高网络的认知性能和智能，从而有助于充分释放大数据的潜力。在这种背景和趋势下，将人工智能前沿推向网络边缘催生了一个新兴的跨学科，即边缘智能（EI）。确实，EI可以将云端的处理能力下沉到边缘侧，在提供实时响应的同时，使能更多高性能的智能服务。然而，EI的成功实现仍处于起步阶段。因此，本文旨在从更广泛的角度对这个年轻领域进行全面的研究。我们首先讨论先验知识，在此基础上我们对EI进行整体概述，包括其关键概念、优势和发展趋势。然后我们重点介绍了EI中的协作模式，并讨论了两个典型案例类别。随后详细阐述了EI中模型训练和推理的整个过程。最后，我们讨论了EI的典型应用场景及其具体体现，并努力阐明一些潜在的挑战，这可能有助于EI从理论到实践的转变。