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. Introduction1. Introduction Part 2. Theory and Algorithm2. Model Inference on Edge Device3. Model Training on Edge Device4. Network Encoding and Quantization Part 3. Architecture Optimization5. DANoC: An Algorithm and Hardware Codesign Prototype6. Ensemble Spiking Networks on Edge Device7. SenseCamera: A Learning Based Multifunctional Smart Camera Prototype