Format:
1 Online-Ressource (1 PDF (xvii, 215 pages))
,
illustrations (some color)
Edition:
Also available in print
ISBN:
9781681739915
Series Statement:
Synthesis lectures on learning, networks, and algorithms #25
Content:
1. Introduction to edge intelligence -- 1.1. Artificial intelligence -- 1.2. Edge computing -- 1.3. Edge intelligence
Content:
2. Edge intelligence via model training -- 2.1. Architectures -- 2.2. Key performance indicators -- 2.3. Enabling technologies -- 2.4. Summary
Content:
3. Edge intelligence via federated meta-learning -- 3.1. Introduction -- 3.2. Related work -- 3.3. Preliminaries on meta-learning -- 3.4. Federated meta-learning for achieving real-time edge intelligence -- 3.5. Performance analysis of FedML -- 3.6. Robust federated meta-learning (FedML) -- 3.7. Experiments -- 3.8. Summary
Content:
4. Edge-cloud collaborative learning via distributionally robust optimization -- 4.1. Introduction -- 4.2. Basic setting for collaborating learning toward edge intelligence -- 4.3. Collaborative learning based on edge-cloud synergy of distribution uncertainty sets -- 4.4. Collaborative learning based on knowledge transfer of conditional prior distribution -- 4.5. Summary
Content:
5. Hierarchical mobile-edge-cloud model training with hybrid parallelism -- 5.1. Introduction -- 5.2. Background and motivation -- 5.3. HierTrain framework -- 5.4. Problem statement of policy scheduling -- 5.5. Optimization of policy scheduling -- 5.6. Performance evaluation -- 5.7. Summary
Content:
6. Edge intelligence via model inference -- 6.1. Architectures -- 6.2. Key performance indicators -- 6.3. Enabling technologies -- 6.4. Summary
Content:
7. On-demand accelerating deep neural network inference via edge computing -- 7.1. Introduction -- 7.2. Background and motivation -- 7.3. Framework and design -- 7.4. Performance evaluation -- 7.5. Summary
Content:
8. Applications, marketplaces, and future directions of edge intelligence -- 8.1. Applications of edge intelligence -- 8.2. Marketplace of edge intelligence -- 8.3. Future directions on edge intelligence.
Content:
With the explosive growth of mobile computing and Internet of Things (IoT) applications, as exemplified by AR/VR, smart city, and video/audio surveillance, billions of mobile and IoT devices are being connected to the Internet, generating zillions of bytes of data at the network edge. Driven by this trend, there is an urgent need to push the frontiers of artificial intelligence (AI) to the network edge to fully unleash the potential of IoT big data. Indeed, the marriage of edge computing and AI has resulted in innovative solutions, namely edge intelligence or edge AI. Nevertheless, research and practice on this emerging inter-disciplinary field is still in its infancy stage. To facilitate the dissemination of the recent advances in edge intelligence in both academia and industry, this book conducts a comprehensive and detailed survey of the recent research efforts and also showcases the authors' own research progress on edge intelligence. Specifically, the book first reviews the background and present motivation for AI running at the network edge. Next, it 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. Finally, it discusses the applications, marketplace, and future research opportunities of edge intelligence. This emerging interdisciplinary field offers many open problems and yet also tremendous opportunities, and this book only touches the tip of iceberg. Hopefully, this book will elicit escalating attention, stimulate fruitful discussions, and open new directions on edge intelligence
Note:
Part of: Synthesis digital library of engineering and computer science
,
Includes bibliographical references (pages 189-211)
,
Compendex
,
INSPEC
,
Google scholar
,
Google book search
,
Also available in print.
,
Mode of access: World Wide Web.
,
System requirements: Adobe Acrobat Reader.
Additional Edition:
ISBN 9781681739922
Additional Edition:
ISBN 9781681739908
Additional Edition:
Erscheint auch als Druck-Ausgabe ISBN 9781681739922
Additional Edition:
ISBN 9781681739908
Language:
English
Keywords:
Electronic books
Bookmarklink
