Guo S. Machine Learning on Commodity Tiny Devices. Theory and Practice 2023

Textbook in PDF format

This book aims at the tiny machine learning (TinyML) software and hardware synergy for edge intelligence applications. It presents on-device learning techniques covering model-level neural network design, algorithm-level training optimization, and hardware-level instruction acceleration. Analyzing the limitations of conventional in-cloud computing would reveal that on-device learning is a promising research direction to meet the requirements of edge intelligence applications. As to the cutting-edge research of TinyML, implementing a high-efficiency learning framework and enabling system-level acceleration is one of the most fundamental issues. This book presents a comprehensive discussion of the latest research progress and provides system-level insights on designing TinyML frameworks, including neural network design, training algorithm optimization and domain-specific hardware acceleration. It identifies the main challenges when deploying TinyML tasks in the real world and guides the researchers to deploy a reliable learning system.
Fundamentals: On-Device Learning Paradigm
Preliminary: Theories and Algorithms
Model-Level Design: Computation Acceleration and Communication Saving
Hardware-Level Design: Neural Engines and Tensor Accelerators
Infrastructure-Level Design: Serverless and Decentralized Machine Learning
System-Level Design: From Standalone to Clusters
Application: Image-Based Visual Perception
Application: Video-Based Real-Time Processing
Application: Privacy, Security, Robustness and Trustworthiness in Edge AI