Deep learning networks are getting smaller. Much smaller. The Google Assistant team can detect words with a model just 14 kilobytes in size—small enough to run on a microcontroller. With this practical book you’ll enter the field of TinyML, where deep learning and embedded systems combine to make astounding things possible with tiny devices. Pete Warden and Daniel Situnayake explain how you can train models small enough to fit into any environment. Ideal for software and hardware developers who want to build embedded systems using machine learning, this guide walks you through creating a series of TinyML projects, step-by-step. No machine learning or microcontroller experience is necessary. Build a speech recognizer, a camera that detects people, and a magic wand that responds to gestures Work with Arduino and ultra-low-power microcontrollers Learn the essentials of ML and how to train your own models Train models to understand audio, image, and accelerometer data Explore TensorFlow Lite for Microcontrollers, Google’s toolkit for TinyML Debug applications and provide safeguards for privacy and security Optimize latency, energy usage, and model and binary size

This book is an effort by AI Technology & Systems to demystify the TinyML technology including market, applications, algorithms, tools and technology. the book dive deeper into the technology beyond common application and keep it light for the readers with varying background including students, hobbyists, managers, market researchers and developers. It starts with introduction to TinyML with benefits and scalability. It introduces no-code and low-code tinyML platform to develop production worthy solutions including audio wake word, visual wake word, American sign language and predictive maintenance. Last two chapters are devoted to sensor and hardware agnostic autoML and tinyML compiler technologies. More information at http://thetinymlbook.com/

Recently, Tiny Machine Learning (TinyML) has gained incredible importance due to its capabilities of creating lightweight machine learning (ML) frameworks aiming at low latency, lower energy consumption, lower bandwidth requirement, improved data security and privacy, and other performance necessities. As billions of battery-operated embedded IoT and low power wide area networks (LPWAN) nodes with very low on-board memory and computational capabilities are getting connected to the Internet each year, there is a critical need to have a special computational framework like TinyML. TinyML for Edge Intelligence in IoT and LPWAN Networks presents the evolution, developments, and advances in TinyML as applied to IoT and LPWANs. It starts by providing the foundations of IoT/LPWANs, low power embedded systems and hardware, the role of artificial intelligence and machine learning in communication networks in general and cloud/edge intelligence. It then presents the concepts, methods, algorithms and tools of TinyML. Practical applications of the use of TinyML are given from health and industrial fields which provide practical guidance on the design of applications and the selection of appropriate technologies. TinyML for Edge Intelligence in IoT and LPWAN Networks is highly suitable for academic researchers and professional system engineers, architects, designers, testers, deployment engineers seeking to design ultra-lower power and time-critical applications. It would also help in designing the networks for emerging and future applications for resource-constrained nodes. - This book provides one-stop solutions for emerging TinyML for IoT and LPWAN applications. - The principles and methods of TinyML are explained, with a focus on how it can be used for IoT, LPWANs, and 5G applications. - Applications from the healthcare and industrial sectors are presented. - Guidance on the design of applications and the selection of appropriate technologies is provided.

Whether you’re a software engineer aspiring to enter the world of deep learning, a veteran data scientist, or a hobbyist with a simple dream of making the next viral AI app, you might have wondered where to begin. This step-by-step guide teaches you how to build practical deep learning applications for the cloud, mobile, browsers, and edge devices using a hands-on approach. Relying on years of industry experience transforming deep learning research into award-winning applications, Anirudh Koul, Siddha Ganju, and Meher Kasam guide you through the process of converting an idea into something that people in the real world can use. Train, tune, and deploy computer vision models with Keras, TensorFlow, Core ML, and TensorFlow Lite Develop AI for a range of devices including Raspberry Pi, Jetson Nano, and Google Coral Explore fun projects, from Silicon Valley’s Not Hotdog app to 40+ industry case studies Simulate an autonomous car in a video game environment and build a miniature version with reinforcement learning Use transfer learning to train models in minutes Discover 50+ practical tips for maximizing model accuracy and speed, debugging, and scaling to millions of users

This book is about making machine learning models and their decisions interpretable. After exploring the concepts of interpretability, you will learn about simple, interpretable models such as decision trees, decision rules and linear regression. Later chapters focus on general model-agnostic methods for interpreting black box models like feature importance and accumulated local effects and explaining individual predictions with Shapley values and LIME. All interpretation methods are explained in depth and discussed critically. How do they work under the hood? What are their strengths and weaknesses? How can their outputs be interpreted? This book will enable you to select and correctly apply the interpretation method that is most suitable for your machine learning project.

This book constitutes the refereed proceedings of five International Workshops held as parallel events of the 18th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2022, virtually and in Hersonissos, Crete, Greece, in June 2022: the 11th Mining Humanistic Data Workshop (MHDW 2022); the 7th 5G-Putting Intelligence to the Network Edge Workshop (5G-PINE 2022); the 1st workshop on AI in Energy, Building and Micro-Grids (AIBMG 2022); the 1st Workshop/Special Session on Machine Learning and Big Data in Health Care (ML@HC 2022); and the 2nd Workshop on Artificial Intelligence in Biomedical Engineering and Informatics (AIBEI 2022). The 35 full papers presented at these workshops were carefully reviewed and selected from 74 submissions.

Low power wide area network (LPWAN) is a promising solution for long range and low power Internet of Things (IoT) and machine to machine (M2M) communication applications. The LPWANs are resource-constrained networks and have critical requirements for long battery life, extended coverage, high scalability, and low device and deployment costs. There are several design and deployment challenges such as media access control, spectrum management, link optimization and adaptability, energy harvesting, duty cycle restrictions, coexistence and interference, interoperability and heterogeneity, security and privacy, and others.LPWAN Technologies for IoT and M2M Applications is intended to provide a one-stop solution for study of LPWAN technologies as it covers a broad range of topics and multidisciplinary aspects of LPWAN and IoT. Primarily, the book focuses on design requirements and constraints, channel access, spectrum management, coexistence and interference issues, energy efficiency, technology candidates, use cases of different applications in smart city, healthcare, and transportation systems, security issues, hardware/software platforms, challenges, and future directions.