
Mobile Edge Artificial Intelligence
Opportunities and Challenges
- 1st Edition - August 7, 2021
- Imprint: Academic Press
- Authors: Yuanming Shi, Kai Yang, Zhanpeng Yang, Yong Zhou
- Language: English
- Paperback ISBN:9 7 8 - 0 - 1 2 - 8 2 3 8 1 7 - 2
- eBook ISBN:9 7 8 - 0 - 1 2 - 8 2 3 8 3 5 - 6
Mobile Edge Artificial Intelligence: Opportunities and Challenges presents recent advances in wireless technologies and nonconvex optimization techniques for designing efficient… Read more

Purchase options

Institutional subscription on ScienceDirect
Request a sales quoteMobile Edge Artificial Intelligence: Opportunities and Challenges presents recent advances in wireless technologies and nonconvex optimization techniques for designing efficient edge AI systems. The book includes comprehensive coverage on modeling, algorithm design and theoretical analysis. Through typical examples, the powerfulness of this set of systems and algorithms is demonstrated, along with their abilities to make low-latency, reliable and private intelligent decisions at network edge. With the availability of massive datasets, high performance computing platforms, sophisticated algorithms and software toolkits, AI has achieved remarkable success in many application domains.
As such, intelligent wireless networks will be designed to leverage advanced wireless communications and mobile computing technologies to support AI-enabled applications at various edge mobile devices with limited communication, computation, hardware and energy resources.
- Presents advanced key enabling techniques, including model compression, wireless MapReduce and wireless cooperative transmission
- Provides advanced 6G wireless techniques, including over-the-air computation and reconfigurable intelligent surface
- Includes principles for designing communication-efficient edge inference systems, communication-efficient training systems, and communication-efficient optimization algorithms for edge machine learning
- Cover image
- Title page
- Table of Contents
- Copyright
- List of figures
- Biography
- Yuanming Shi
- Kai Yang
- Zhanpeng Yang
- Yong Zhou
- Preface
- Acknowledgments
- Part One: Introduction and overview
- Chapter One: Motivations and organization
- Abstract
- 1.1. Motivations
- 1.2. Organization
- References
- Chapter Two: Primer on artificial intelligence
- Abstract
- 2.1. Basics of machine learning
- 2.2. Models of deep learning
- 2.3. Summary
- References
- Chapter Three: Convex optimization
- Abstract
- 3.1. First-order methods
- 3.2. Second-order methods
- 3.3. Summary
- References
- Chapter Four: Mobile edge AI
- Abstract
- 4.1. Overview
- 4.2. Edge inference
- 4.3. Edge training
- 4.4. Coded computing
- 4.5. Summary
- References
- Part Two: Edge inference
- Chapter Five: Model compression for on-device inference
- Abstract
- 5.1. Background on model compression
- 5.2. Layerwise network pruning
- 5.3. Nonconvex network pruning method with log-sum approximation
- 5.4. Simulation results
- 5.5. Summary
- References
- Chapter Six: Coded computing for on-device cooperative inference
- Abstract
- 6.1. Background on MapReduce
- 6.2. A communication-efficient data shuffling scheme
- 6.3. A low-rank optimization framework for communication-efficient data shuffling
- 6.4. Numerical algorithms
- 6.5. Simulation results
- 6.6. Summary
- References
- Chapter Seven: Computation offloading for edge cooperative inference
- Abstract
- 7.1. Background
- 7.2. Energy-efficient wireless cooperative transmission for edge inference
- 7.3. Computationally tractable approximation for probabilistic QoS constraints
- 7.4. Reweighted power minimization approach with DC regularization
- 7.5. Simulation results
- 7.6. Summary
- References
- Part Three: Edge training
- Chapter Eight: Over-the-air computation for federated learning
- Abstract
- 8.1. Background of federated learning and over-the-air computation
- 8.2. System model
- 8.3. Fast model aggregation via over-the-air computation
- 8.4. Sparse and low-rank optimization framework
- 8.5. Numerical algorithms
- 8.6. Simulation results
- 8.7. Summary
- References
- Chapter Nine: Reconfigurable intelligent surface aided federated learning
- Abstract
- 9.1. Background on reconfigurable intelligent surface
- 9.2. RIS empowered on-device distributed federated learning
- 9.3. Sparse and low-rank optimization framework
- 9.4. Simulation results
- 9.5. Summary
- References
- Chapter Ten: Blind over-the-air computation for federated learning
- Abstract
- 10.1. Blind over-the-air computation
- 10.2. Problem formulation
- 10.3. Wirtinger flow algorithm for blind over-the-air computation
- 10.4. Numerical results
- 10.5. Summary
- References
- Part Four: Final part: conclusions and future directions
- Chapter Eleven: Conclusions and future directions
- Abstract
- 11.1. Conclusions
- 11.2. Discussions and future directions
- Index
- Edition: 1
- Published: August 7, 2021
- Imprint: Academic Press
- No. of pages: 206
- Language: English
- Paperback ISBN: 9780128238172
- eBook ISBN: 9780128238356
YS
Yuanming Shi
KY
Kai Yang
ZY
Zhanpeng Yang
YZ