Chapter 1, Principles and Foundations of IoT and AI, introduces the basic concepts IoT, AI, and data science. We end the chapter with an introduction to the tools and datasets we will be using in the book.
Chapter 2, Data Access and Distributed Processing for IoT, covers various methods of accessing data from various data sources, such as files, databases, distributed data stores, and streaming data.
Chapter 3, Machine Learning for IoT, covers the various aspects of machine learning, such as supervised, unsupervised, and reinforcement learning for IoT. The chapter ends with tips and tricks to improve your models' performance.
Chapter 4, Deep Learning for IoT, explores the various aspects of deep learning, such as MLP, CNN, RNN, and autoencoders for IoT. It also introduces various frameworks for deep learning.
Chapter 5, Genetic Algorithms for IoT, discusses optimization and different evolutionary techniques employed for optimization with an emphasis on genetic algorithms.
Chapter 6, Reinforcement Learning for IoT, introduces the concepts of reinforcement learning, such as policy gradients and Q-networks. We cover how to implement deep Q networks using TensorFlow and learn some cool real-world problems where reinforcement learning can be applied.
Chapter 7, Generative Models for IoT, introduces the concepts of adversarial and generative learning. We cover how to implement GAN, DCGAN, and CycleGAN using TensorFlow, and also look at their real-life applications.
Chapter 8, Distributed AI for IoT, covers how to leverage machine learning in distributed mode for IoT applications.
Chapter 9, Personal and Home and IoT, goes over some exciting personal and home applications of IoT.
Chapter 10, AI for Industrial IoT, explains how to apply the concepts learned in this book to two case studies with industrial IoT data.
Chapter 11, AI for Smart Cities IoT, explains how to apply the concepts learned in this book to IoT data generated from smart cities.
Chapter 12, Combining It All Together, covers how to pre-process textual, image, video, and audio data before feeding it to models. It also introduces time series data.
