Edge AI : convergence of edge computing and artificial intelligence
Author(s)
Bibliographic Information
Edge AI : convergence of edge computing and artificial intelligence
Springer, c2020
- : hardback
Available at / 1 libraries
-
No Libraries matched.
- Remove all filters.
Note
Other authors: Yiwen Han, Victor C. M. Leung, Dusit Niyato, Xueqiang Yan, Xu Chen
Includes bibliographical references
Description and Table of Contents
Description
As an important enabler for changing people's lives, advances in artificial intelligence (AI)-based applications and services are on the rise, despite being hindered by efficiency and latency issues. By focusing on deep learning as the most representative technique of AI, this book provides a comprehensive overview of how AI services are being applied to the network edge near the data sources, and demonstrates how AI and edge computing can be mutually beneficial. To do so, it introduces and discusses: 1) edge intelligence and intelligent edge; and 2) their implementation methods and enabling technologies, namely AI training and inference in the customized edge computing framework. Gathering essential information previously scattered across the communication, networking, and AI areas, the book can help readers to understand the connections between key enabling technologies, e.g. a) AI applications in edge; b) AI inference in edge; c) AI training for edge; d) edge computing for AI; and e) using AI to optimize edge. After identifying these five aspects, which are essential for the fusion of edge computing and AI, it discusses current challenges and outlines future trends in achieving more pervasive and fine-grained intelligence with the aid of edge computing.
Table of Contents
1: Introduction
2: Fundamentals of Edge Computing
2.1 Paradigms of Edge Computing
Cloudlet and Micro Data Centers
Fog Computing
Mobile (Multi-access) Edge Computing (MEC)
Definition of Edge Computing Terminologies
Collaborative End-Edge-Cloud Computing
2.2 Hardware for Edge Computing
AI Hardware for Edge Computing
Integrated Commodities Potentially for Edge Nodes
Edge Computing Frameworks
2.3 Virtualizing the Edge
Virtualization Techniques
Network Virtualization
Network Slicing
3. Fundamentals of Deep Learning
3.1 Neural Networks in Deep Learning
Fully Connected Neural Network (FCNN)
Auto-Encoder (AE)
Convolutional Neural Network (CNN)
Generative Adversarial Network (GAN)
Recurrent Neural Network (RNN)
Transfer Learning (TL)
3.2 Deep Reinforcement Learning (DRL)
Value-based DRL
Policy-gradient-based DRL
3.3 Distributed DL Training
3.4 Potential DL Libraries for Edge
4. Deep Learning Applications on Edge
4.1 Real-time Video Analytic
4.2 Autonomous Internet of Vehicles (IoVs)
4.3 Intelligent Manufacturing
4.4 Smart Home and City
5. Deep Learning Inference in Edge
5.1 Optimization of DL Models in Edge
General Methods for Model Optimization
Model Optimization for Edge Devices
5.2 Segmentation of DL Models
5.3 Early Exit of Inference (EEoI)
5.4 Sharing of DL Computation
6. Edge Computing for Deep Learning
6.1 Edge Hardware for DL
Mobile CPUs and GPUs
FPGA-based Solutions
6.2 Communication and Computation Modes for Edge DL
Integral Offloading
Partial Offloading
Vertical Collaboration
Horizontal Collaboration
6.3 Tailoring Edge Frameworks for DL
6.4 Performance Evaluation for Edge DL
7. Deep Learning Training at Edge
7.1 Distributed Training at Edge
7.2 Vanilla Federated Learning at Edge
7.3 Communication-efficient FL
7.4 Resource-optimized FL
7.5 Security-enhanced FL
8. Deep Learning for Optimizing Edge
8.1 DL for Adaptive Edge Caching
8.2 DL for Optimizing Edge Task Offloading
8.3 DL for Edge Management and Maintenance
Edge Communication
Edge Security
Joint Edge Optimization
9. Lessons Learned and Open Challenges
9.1 More Promising Applications
9.2 General DL Model for Inference
9.3 Complete Edge Architecture for DL
9.4 Practical Training Principles at Edge
9.5 Deployment and Improvement of Intelligent Edge
by "Nielsen BookData"
