Authors | |
Publisher | Springer, Berlin |
Year | |
Pages | 149 |
Version | paperback |
Language | English |
ISBN | 9789811561887 |
Categories | Artificial intelligence |
Edge AI: Convergence of Edge Computing and Artificial Intelligence
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 ComputingAI 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 OffloadingPartial 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 Edge7.3 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