Wednesday, June 30, 2021

Machine Learning for Beginners, Curriculum

It is our very great pleasure to announce the release of a new, free, MIT-licensed open-source curriculum all about classic Machine Learning: Machine Learning for Beginners. Brought to you by a team of Azure Cloud Advocates and Program Managers, we hope to empower students of all ages to learn the basics of ML. Presuming no knowledge of ML, we offer a free 12-week, 24-lesson curriculum, plus a bonus 'postscript' lesson to help you dive into this amazing field.

If you liked our first curriculum, Web Dev for Beginners, you will love Machine Learning for Beginners!

 

Join us on a voyage!

Travel around the world in this themed semester-long self-study course as we look at ML topics through the lens of world cultures.

 

Our curricula are structured with a modified Project-Based pedagogy and include:

  • a pre-lesson warmup quiz
  • a written lesson
  • video
  • knowledge checks
  • a project to build
  • infographics, sketchnotes, and visuals
  • a challenge
  • an assignment
  • a post-lesson quiz
  • a 'PAT' (see below)
  • opportunities to deepen your knowledge on Microsoft Learn

 

Meet the team!

 

 

What will you learn?

 

The lessons are grouped so that you can deep-dive into various important aspects of classic ML. We start with an introduction to ML concepts, moving to its history, concepts of fairness in machine learning, and discussing the tools and techniques of the trade. We then move on to Regression, Classification, Clustering, Natural Language Processing, Time Series Forecasting, Reinforcement Learning, with two 'applied' lessons demonstrating how to use your models within web apps for inference. We end with a 'postscript' lesson listing "real-world" applications of ML, showing how these techniques are used "in the wild".

To make it easy for new learners to get started with ML, we built the content so that it can be used offline and so that the exercises can be completed using .ipynb notebooks within Visual Studio Code. Grab your datasets and let's go!

This curriculum is all about "classic Machine Learning", so we tackle these basic concepts for the most part using Scikit-learn, a library that helps demystify and explain these concepts. We don't discuss deep learning or neural networks in this ML curriculum, but please stay tuned as we release our AI for Beginners curriculum this Fall!

Travel with us to discover North American pumpkin market pricing (Regression), Pan-Asian cuisines (Classification), Nigerian musical tastes (Clustering), European Hotel Reviews (NLP), World electricity usage (Time Series) and the Russian story about Peter and the Wolf (Reinforcement Learning).

 

How to use this curriculum: meet PAT

 

This is a self-study course, but it works well in groups so consider finding study buddies and learning together. Warm up with a pre-lesson low-stakes quiz and work through the lessons and assignments together or solo. Test your knowledge with the post-lesson quiz.

New for this curriculum is the use of Progress Assessment Tools in the Discussion Board area. Once done with a lesson group, visit the Discussion Board and copy the template to a new Discussion using the "quote reply". Fill in your learnings in the self-reflection box and respond to other students in the repo. Let's learn together!

We are also open to PRs and Issue raising, following our Code of Conduct and templating systems. We hope the community will chip in with translations of the lessons, quizzes and assignments. Thank you for participating as we learn together.

 

A sneak peek

 

This curriculum is filled with a lot of art, created by our team. Take a look at this cool sketchnote created by @girlie_mac .

Chris_Noring_1-1625058142891.jpeg

 

Without further ado, please meet Machine Learning For Beginners: A Curriculum!

 

You need to LEARN Python?

Here's our best recommendations from LEARN:

 

https://docs.microsoft.com/en-us/learn/modules/intro-to-python/

- https://docs.microsoft.com/en-us/learn/paths/python-first-steps/

 

 

 

Posted at https://sl.advdat.com/3drVIOq