Embedded Intelligence: State-of-the-Art and Research Challenges

Recent years have seen deployments of increasingly complex artificial intelligent (AI) and machine learning techniques being implemented on cloud server architectures embedded into edge computing devices for supporting Internet Things (IoT) mobile applications. It is important to note that these intelligence (EI) servers significant differences in terms objectives, models, platforms research challenges. This paper presents a comprehensive survey EI from four aspects: (1) First, the state-of-the-art using set evaluation criteria proposed reviewed; (2) Second, both accelerators low-complexity are discussed; (3) Third, various categorized discussed system, algorithm, architecture technology levels; (4) The concludes with lessons learned future prospects key role likely play emerging technologies applications such as Industry 4.0. aims give useful insights developments this area study highlight challenges practical deployments.