Deep Learning on Edge Computing Devices: Design Challenges of Algorithm and Architecture focuses on hardware architecture and embedded deep learning, including neural networks. The title helps researchers maximize the performance of Edge-deep learning models for mobile computing and other applications by presenting neural network algorithms and hardware design optimization approaches for Edge-deep learning. Applications are introduced in each section, and a comprehensive example, smart surveillance cameras, is presented at the end of the book, integrating innovation in both algorithm and hardware architecture. Structured into three parts, the book covers core concepts, theories and algorithms and architecture optimization.
This book provides a solution for researchers looking to maximize the performance of deep learning models on Edge-computing devices through algorithm-hardware co-design.
1. Chapter 1 : Introduction - p. Page x 2. Chapter 2 : The basics of deep learning - p. Page 16 3. Chapter 3 : Model design and compression - p. Page 34 4. Chapter 4 : Mix-precision model encoding and quantization - p. Page 56 5. Chapter 5 : Model encoding of binary neural networks - p. Page 73 6. Chapter 6 : Binary neural network computing architecture - p. Page 92 7. Chapter 7 : Algorithm and hardware codesign of sparse binary network on-chip - p. Page 108 8. Chapter 8 : Hardware architecture optimization for object tracking - p. Page 135 9. Chapter 9 : SensCamera: A learning-based smart camera prototype - p. Page 152 10. Index - p. Page 175
Deep Learning on Edge Computing Devices: Design Challenges of Algorithm and Architecture focuses on hardware architecture and embedded deep learning, including neural networks. The title helps researchers maximize the performance of Edge-deep learning models for mobile computing and other applications by presenting neural network algorithms and hardware design optimization approaches for Edge-deep learning. Applications are introduced in each section, and a comprehensive example, smart surveillance cameras, is presented at the end of the book, integrating innovation in both algorithm and hardware architecture. Structured into three parts, the book covers core concepts, theories and algorithms and architecture optimization.
This book provides a solution for researchers looking to maximize the performance of deep learning models on Edge-computing devices through algorithm-hardware co-design.
1. Chapter 1 : Introduction - p. Page x 2. Chapter 2 : The basics of deep learning - p. Page 16 3. Chapter 3 : Model design and compression - p. Page 34 4. Chapter 4 : Mix-precision model encoding and quantization - p. Page 56 5. Chapter 5 : Model encoding of binary neural networks - p. Page 73 6. Chapter 6 : Binary neural network computing architecture - p. Page 92 7. Chapter 7 : Algorithm and hardware codesign of sparse binary network on-chip - p. Page 108 8. Chapter 8 : Hardware architecture optimization for object tracking - p. Page 135 9. Chapter 9 : SensCamera: A learning-based smart camera prototype - p. Page 152 10. Index - p. Page 175
