Chapter 1, Setting Up the IoT and AI Environment, will focus on getting the right environment set up for success. You will learn how to choose a device that meets your needs for AI, whether that model needs to be on the edge or in the cloud. You will also learn how to securely communicate with modules within a device, other devices, or the cloud. Finally, you will set up a way to ingest data in the cloud and then set up Spark and AI tools to perform analysis of data, train models, and run machine learning models at scale.
Chapter 2, Handling Data, talks about the basics of ensuring that data in any format can be used by data scientists effectively.
Chapter 3, Machine Learning for IoT, will discuss using machine learning models such as logistic regression and decision trees to solve common IoT issues such as classifying medical results, detecting unsafe drivers, and classifying chemical readings.
Chapter 4, Deep Learning for Predictive Maintenance, will focus on various classification techniques to enable IoT devices to be smart devices.
Chapter 5, Anomaly Detection, will explain how when alarm detection does not classify a particular issue, it can lead to the discovery of issues, and how if a device is acting in an anomalous way, you might want to send out a repair worker to examine the device.
Chapter 6, Computer Vision, will discuss implementing computer vision in the cloud as well as on edge devices such as NVIDIA Jetson Nano.
Chapter 7, NLP and Bots for a Self-Ordering Kiosk, will discuss using NLP and using bots to enable interaction with users ordering foods at a restaurant kiosk.
Chapter 8, Optimizing with Microcontrollers and Pipelines, will discuss how reinforcement learning can be used with a smart traffic intersection to make traffic light decisions that decrease the wait time at traffic lights and allow traffic to flow better.
Chapter 9, Deploying to the Edge, will discuss various ways of applying pre-trained machine learning models to an edge device. This chapter will discuss IoT Edge in detail. Deploying is an important part of the AI pipeline. This chapter will also talk about deploying machine learning models to web applications and mobile using TensorFlow.js and ONNX.