CHAPTER 14
Building AI Models
Now that you’ve trained your very first artificial intelligence (AI) model and used it in a Scratch project, it’s time to level up! In this final chapter, you’ll create a brand-new model using image recognition, which means your program can “see” what’s in a picture. Specifically, you’ll build a fun, interactive Scratch project called Pico’s Colors where a sprite friend named Pico looks through your camera and tells you what it sees (specifically, what color it sees) — similar to how an AI-powered robot with computer vision reacts to its environment.
Image recognition is a powerful part of AI. It’s used in self-driving cars that read road signs, apps that identify plants and animals, and smart robots that can sort recycling or help doctors look at X-rays. By training your own color-recognizing model, you’ll learn how to give your code “eyes” to explore the world. Importantly, you’ll also discover that training a useful, accurate model requires a lot of data, time, and revisions. But as you level up, you’re building the skills and mindset needed to create real value for real people — and preparing for amazing tech careers in your future!

Generated with AI using DALL·E – OpenAI
Brainstorming Machine Learning Image Models
From tinkering with Machine Learning for Kids (ML4K) in Chapter 13, you learned the basics of AI and building a machine learning ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access