Introduction to ML
About this free Introduction to ML course
Introduction to ML is a free, beginner-friendly machine learning course that explains how computers learn from data without step-by-step instructions, and with no coding required. It's a short, concept-first course that gives students the vocabulary and intuition to understand the AI tools they use every day.
Students learn the three main paradigms of learning: supervised, unsupervised, and reinforcement learning. They see how models connect features to labels, why training data lets a computer practice before it's checked on testing data, and why a model might confuse a chihuahua with a blueberry muffin. The course also takes AI ethics seriously, covering fairness, honesty, and removing bias from human-provided data. It closes with real-world applications, from house price prediction and spam detection to disease detection and climate change tracking.
Who this course is for
This course is designed for students in grades 6 through 10 who are curious about artificial intelligence and have no programming or advanced math background. It's also a quick primer for older students before they start Intro to Machine Learning.
Course outline
- What is machine learning? How ML teaches computers to learn patterns without step-by-step instructions.
- Three ways machines learn. Supervised learning with labeled examples, unsupervised learning that finds patterns on its own, and reinforcement learning through rewards and penalties.
- Features and labels. How supervised models connect pieces of information (features) to answers (labels).
- Training and testing data. Why models practice on training data and are checked on testing data.
- When models get it wrong. Tricky features, like the chihuahua-vs-muffin problem, and how careful training helps.
- The ethics of machine learning. Fairness, honesty, and removing bias from human-provided data.
- Real-world applications. House price prediction, spam detection, disease detection, and climate change tracking.
What you'll learn
- Explain what machine learning is in plain language
- Compare supervised, unsupervised, and reinforcement learning
- Identify features and labels in a real dataset
- Explain why models need separate training and testing data
- Recognize how bias enters AI systems and how to reduce it
How long it takes
This is a short course. Plan on about 4 hours, which fits into a single week or a couple of club meetings.
Frequently asked questions about Introduction to ML
Is Introduction to ML really free?
Yes. Introduction to ML is completely free, with no fees, subscriptions, or account required. STEM for Others is a 501(c)(3) nonprofit, and every course in our curriculum library is free for students, families, and teachers.
Do I need to know how to code?
No. Introduction to ML is entirely conceptual. When you're ready to build real models, Intro to Python and Intro to Machine Learning are the next steps.
How do I start the course?
Click Begin Course at the top of this page to open the full slide deck in a new tab. You can also flip through the slides embedded above. Work through one unit at a time and try the practice questions before moving on.
Do I get a certificate?
The self-paced Introduction to ML materials don't include an official certificate. If you're taking the course through a STEM for Others chapter program, ask your chapter leader about recognizing your completion.
Can teachers and clubs use this curriculum?
Yes. Teachers, homeschool families, libraries, and after-school clubs are welcome to use the Introduction to ML materials with their students at no cost. STEM for Others volunteers also teach our curriculum in partner schools and libraries. You can find a chapter near you or start one at your school.
Related free courses
