Deep Learning on Edge Computing Devices
Design Challenges of Algorithm and Architecture

Helps users maximize the performance of deep learning on Edge-computing devices

Xichuan Zhou (Author), Haijun Liu (Author), Cong Shi (Author), Ji Liu (Author)

9780323857833, Elsevier Science

Paperback / softback, published 7 February 2022

198 pages, 35 illustrations (15 in full color)
22.9 x 15.2 x 1.4 cm, 0.41 kg

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.

Part 1. Introduction
1. Introduction
 
Part 2. Theory and Algorithm
2. Model Inference on Edge Device
3. Model Training on Edge Device
4. Network Encoding and Quantization
 
Part 3. Architecture Optimization
5. DANoC: An Algorithm and Hardware Codesign Prototype
6. Ensemble Spiking Networks on Edge Device
7. SenseCamera: A Learning Based Multifunctional Smart Camera Prototype

Subject Areas: Machine learning [UYQM], Artificial intelligence [UYQ]