- ホーム
- > 洋書
- > ドイツ書
- > Mathematics, Sciences & Technology
- > Technology
- > electronics, electrical engineering, telecommunications
Full Description
This book conducts a comprehensive and detailed survey of the recent research efforts in edge intelligence. The authors first review the background and present motivation for AI running at the network edge. The book then provides an overview of the overarching architectures, frameworks, and emerging key technologies for deep learning models toward training/inference at the network edge. To illustrate the research problems for edge intelligence, the book also showcases four of the authors' own research projects on edge intelligence, ranging from rigorous theoretical analysis to studies based on realistic implementation. This second edition incorporates the latest research in this rapidly developing area. The authors also highlight the current applications and future research opportunities for edge intelligence.
Contents
Introduction to Edge Intelligence.- Edge Intelligence via Model Training.- Edge Intelligence via Federated Meta-Learning.- Resource-efficient Edge AI via Personalized Federated Learning.- Edge-Cloud Collaborative Learning via Distributionally Robust Optimization.- Hierarchical Mobile-Edge-Cloud Model Training with Hybrid Parallelism.- Communication-Efficient Hierarchical Federated Edge Learning.- Edge Intelligence via Model Inference.- On-Demand Accelerating Deep Neural Network Inference via Edge Computing.- Cooperative Edge DNN Inference with Adaptive Workload Partitioning.- Online Optimization and Resource Provisioning for Edge DNN Inference.- Applications, Marketplaces, and Future Directions of Edge Intelligence.