Machine Learning for Beginners: A Free 26-Lesson Curriculum

7月10日 Published inMachine Learning

This curriculum consists of 26 lessons organized into nine modules. The program is designed to guide you from foundational concepts to practical, real-world applications.

Lesson	Topic	Module	Learning Goal	Language / Author
01	Intro to ML	Introduction	Understand core concepts	Muhammad
02	History of ML	Introduction	Learn how the field evolved	Jen & Amy
03	ML & Fairness	Introduction	Explore ethical considerations in ML development	Tomomi
04	ML Techniques	Introduction	Review common techniques used by researchers	Chris & Jen
05	Regression Intro	Regression	Build regression models with Python and Scikit-learn	Jen / Eric Wanjau
06	North American Pumpkin Prices 🎃	Regression	Prepare data: visualization and cleaning	Jen / Eric Wanjau
07	North American Pumpkin Prices 🎃	Regression	Build linear and polynomial regression models	Jen & Dmitry / Eric Wanjau
08	North American Pumpkin Prices 🎃	Regression	Build a logistic regression model	Jen / Eric Wanjau
09	Web App 🔌	Web App	Build a web application using a trained model	Jen
10	Classification Intro	Classification	Clean, prepare, and visualize data for classification	Jen & Cassie / Eric Wanjau
11	Asian & Indian Cuisine 🍜	Classification	Get started with basic classifiers	Jen & Cassie / Eric Wanjau
12	Asian & Indian Cuisine 🍜	Classification	Implement advanced classifiers	Jen & Cassie / Eric Wanjau
13	Asian & Indian Cuisine 🍜	Classification	Build a recommendation web app from your model	Jen
14	Clustering Intro	Clustering	Clean, prepare, and visualize data for clustering	Jen / Eric Wanjau
15	Nigerian Music Preferences 🎧	Clustering	Explore K-Means clustering	Jen / Eric Wanjau
16	NLP Intro ☕️	Natural Language Processing	Learn NLP basics by building a simple bot	Stephen
17	Common NLP Tasks ☕️	Natural Language Processing	Study language structure and processing	Stephen
18	Translation & Sentiment ♥️	Natural Language Processing	Analyze sentiment and translate Jane Austen’s work	Stephen
19	Romantic Hotels of Europe ♥️	Natural Language Processing	Hotel review sentiment analysis (Part 1)	Stephen
20	Romantic Hotels of Europe ♥️	Natural Language Processing	Hotel review sentiment analysis (Part 2)	Stephen
21	Time Series Intro	Time Series	Learn the fundamentals of time series forecasting	Francesca
22	⚡️ Worldwide Electricity Usage ⚡️	Time Series	Forecast usage with ARIMA	Francesca
23	⚡️ Worldwide Electricity Usage ⚡️	Time Series	Forecast usage with Support Vector Regressor (SVR)	Anirban
24	Reinforcement Learning Intro	Reinforcement Learning	Learn RL fundamentals with Q-Learning	Dmitry
25	Help Peter Avoid the Wolf! 🐺	Reinforcement Learning	Hands-on RL using the Gym library	Dmitry
Postscript	Real-world ML Scenarios & Applications	Real-world ML	Review classic ML applications in industry	Team
Postscript	Debug ML Models with RAI Dashboard	Real-world ML	Debug models using Responsible AI components	Ruth Yakubu

The curriculum is built on two core principles: project-based learning and frequent assessment. A consistent theme runs through the lessons to ensure the material remains cohesive.

Project-based learning helps ensure that concepts are retained through practice. Pre-lecture quizzes establish clear learning goals, while post-lecture quizzes reinforce memory. The material is flexible; you can complete the entire 12-week program or select specific lessons as needed. The course begins with simple concepts and gradually increases in complexity. The postscript lessons serve as extra credit or starting points for further discussion.

Each lesson includes:

Optional sketch notes
Optional video links (including full walkthroughs for some lessons)
A pre-lecture warm-up quiz
Written instructional content
Step-by-step guides for project-based lessons
Knowledge checks
Practical challenges and assignments
Supplemental reading
A post-lecture quiz

Language & Quiz Notes

While most lessons use Python, several also include R versions. You can find these in the solution folder of each lesson as .rmd files (R Markdown). These files integrate code blocks and YAML headers within Markdown, making them ideal for data science work that needs to be exported to PDF, HTML, or Word.

There are 52 quizzes located in the quiz-app folder, each containing three questions. Links to these quizzes are provided within the individual lessons. To run the quizzes locally, follow the instructions in the quiz-app directory. They can be hosted on your local machine or deployed to Azure.

How to Start

Fork the repository – Click the “Fork” button in the top right corner of the GitHub page.
Clone the repository – Run the following command: git clone https://github.com/microsoft/ML-For-Beginners.git
Microsoft Learn – Course resources are also accessible via Microsoft Learn collections.

Student Guide:

Fork the entire repository to your personal GitHub account to work individually or with a team.
Take the pre-lecture quiz to gauge your initial understanding.
Read through the lesson, pausing at each knowledge check.
Complete the project. We recommend reviewing the material thoroughly before starting. Solution code is available in the /solution folder of each project lesson, but should only be used if you get stuck.
Take the post-lecture quiz to confirm what you’ve learned.
Complete the assigned challenge and homework.
After finishing a module, visit the discussion board. Use the PAT (Progress Assessment Tool) scorecard to share your progress and interact with other students' entries.

For further study, explore the dedicated Microsoft Learn modules and learning paths. Educators can also find tips for classroom implementation within the course materials.

Extra Resources

Video Walkthroughs – Select lessons feature short videos. These are linked within the lessons, or you can view the "ML for Beginners" playlist on the Microsoft Developer YouTube channel.
Offline Access – You can use Docsify to view the course offline. Fork the repo, install Docsify on your machine, and run docsify serve in the root folder. You can then access the site at localhost:3000.
PDF Version – A PDF version of the course with active links is available for download.

▶ Visit

Related Tools

Machine Learning for Beginners: A Free 26-Lesson Curriculum

Transformers Library: Installation, Pipeline API, and Model Examples

ZeroSearch: Training LLMs to Search Without Real-World Search Engines

Infinite Radio: The AI DJ That Adapts Music Genres to Your Screen