🌍 Travel around the world as we explore Machine Learning by means of world cultures 🌍
Aalborg University and Microsoft are pleased to offer a 12-week, 26-lesson curriculum about Machine Learning. In this curriculum, you will learn about what is sometimes called classic machine learning, using primarily Scikit-learn as a library.
Travel with us around the world as we apply these classic techniques to data from many areas of the world. Each lesson includes pre- and post-lesson quizzes, written instructions to complete the lesson, a solution, an assignment, and more. Our project-based pedagogy allows you to learn while building, a proven way for new skills to 'stick'.
To use this curriculum out of the box, visit the AAU JupyterHub (link at Moodle).
You can also fork the entire repo and complete the exercises on your own or with a group.
In any case
- Start with a pre-lecture quiz.
- Read the lecture and complete the activities, pausing and reflecting at each knowledge check.
- Try to create the projects by comprehending the lessons rather than running the solution code; however that code is available in the
/solutionfolders in each project-oriented lesson. - Take the post-lecture quiz.
- Complete the challenge.
- Complete the assignment.
- Submit it to via JupyterHub (we can also try Github Classroom as a pull request).
For further study, we recommend following the link to the Microsoft Learn modules and learning paths.
Gif by Mohit Jaisal
🎥 Click the image above for a video about the project and the Microsoft folks who created it!
We have chosen two pedagogical tenets while building this curriculum: ensuring that it is hands-on project-based and that it includes frequent quizzes. In addition, this curriculum has a common theme to give it cohesion.
By ensuring that the content aligns with projects, the process is made more engaging for students and retention of concepts will be augmented. In addition, a low-stakes quiz before a class sets the intention of the student towards learning a topic, while a second quiz after class ensures further retention. This curriculum was designed to be flexible and fun and can be taken in whole or in part. The projects start small and become increasingly complex by the end of the 12-week cycle. This curriculum also includes a postscript on real-world applications of ML, which can be used as extra credit or as a basis for discussion.
Find Microsoft's' Code of Conduct, Contributing, and Translation guidelines in the links. In 2022, your teachers are Cumhur Erkut, George Palamas, and Henrique Galvan Debarba.
- optional sketchnote
- optional supplemental video
- pre-lecture warmup quiz
- written lesson
- for project-based lessons, step-by-step guides on how to build the project
- knowledge checks
- a challenge
- supplemental reading
- assignment
- post-lecture quiz
A note about quizzes: All quizzes are contained in this app, for 52 total quizzes of three questions each. They are linked from within the lessons. Multiple lessons will be contained in Sessions, which are the sessions you'll also see at Moodle.
Below is a preliminary schedule, which mainly follows Microsoft's ML for beginners, from our own fork at https://github.com/SMC-AAU-CPH/ML-For-Beginners
| Sec | Date | Theory | Teacher | Lesson Group | Lessons | Learning objectives addressed |
|---|---|---|---|---|---|---|
| 1 | <2022-09-02 Fri> | Introduction | Cumhur | Introduction | 1-4 | Multivariate statistics |
| 2 | <2022-09-08 Thu> | Supervised Learning I | Cumhur | Regression | 5-8 | Least-squares, ANN afterAI-For-Beginners |
| 3 | <2022-09-15 Thu> | Supervised learning II | George | Classification | 10-12 | Bayesian, parametric, non-parametric, CNNs |
| 4 | <2022-09-22 Thu> | Unsupervised Learning I | George | Clustering & Vizualization | 14-15 | k-means, GMMs, PCA, autoencoder |
| 5 | <2022-09-29 Thu> | Unsupervised Learning II | George | Procedural Cont. Gen andNLP | 16-20 | Context and application |
| 7 | <2022-10-06 Thu> | Reinforcement Learning | Henrique | Reinforcement learning | 24,25 | Q-learning, Gym |
| 8 | <2022-10-13 Thu> | Workshop I: Deployment | Cumhur | WebApp, gradio, streamlit | 9,13 | Application to media |
| 9 | <2022-11-03 Thu> | Real-world, EU regulations | Cumhur | ML in the Wild, with T. Bjørner | Social aspects (from last year) | |
| 10 | <2022-11-10 Thu> | Time-series analysis ? | Henrique | Time series / own research | 21-23 | E.g., movement {Geleijn:2021ds} |
| 11 | <2022-11-17 Thu> | Workshop II: mini-projects | Cumhur | And a Guest | ||
| 12 | <2022-11-24 Thu> | Wrap up, mini-projects | ALL | If needed! |
Microsoft team produces other curricula! Check out: