Abstract
In this chapter, we introduce the concept of EdgeAI, followed by a brief talk on how AI benefits edge computing and vice versa. We then move to discuss the variety of architectures that may be adopted for implementing AI at the edge, explicitly elaborating on training and inference architectures separately. Next, we provide a holistic view of the different criteria to evaluate the processes of Model Training and Model Inference at the edge. We then review emerging frameworks and technologies which assist the training and inference processes by targeting and improving specific Key Performance Indicators (KPIs). We also analyze how each enabling technology impacts the different KPIS for both the training and inference process. Finally, we summarize all the architectures, criteria for evaluating AI model workflow, and the enabling technologies for model training and inference at the edge in the form of a comparative analysis.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.