Home
Login

Stage 2: Classic Machine Learning

A classic 12-week, 26-lesson machine learning curriculum for beginners developed by Microsoft, learning machine learning through practical application with cultural data from around the world.

MachineLearningPythonScikit-learnGitHubTextFreeEnglish

ML-For-Beginners Project Detailed Introduction

Project Overview

ML-For-Beginners is a comprehensive machine learning tutorial project for beginners developed by the Microsoft Cloud Advocate team. It is a 12-week, 26-lesson, 52-quiz classic machine learning curriculum focused on exploring machine learning using cultural data from around the world.

Core Features

  • 🌍 Global Perspective: Learn machine learning through cultural data from around the world.
  • 📚 Systematic Curriculum: A complete 12-week curriculum with 26 detailed lessons.
  • 🧪 Practice-Oriented: Project-based teaching method, learning by doing.
  • 🔍 Assessment System: Includes 52 quizzes, with pre- and post-lesson assessments.
  • 🎯 Classic Machine Learning: Primarily uses the Scikit-learn library, avoiding deep learning content.

Teaching Philosophy

Two Core Teaching Principles

  1. Hands-on Practice: Ensure all content is based on project-based practical learning.
  2. Frequent Assessment: Ensure learning effectiveness through pre- and post-lesson quizzes.

Course Structure

Each lesson includes the following components:

  • Optional sketchnote
  • Optional supplementary video
  • Video demonstration (some lessons)
  • Pre-lesson warm-up quiz
  • Written lesson content
  • Project-based step-by-step guide
  • Knowledge checkpoints
  • Challenge exercises
  • Supplementary reading materials
  • Assignment
  • Post-lesson quiz

Complete Course Outline

Lessons 1-4: Introduction to Machine Learning Fundamentals

  • Lesson 1: Introduction to Machine Learning
  • Lesson 2: History of Machine Learning
  • Lesson 3: Fairness in Machine Learning
  • Lesson 4: Machine Learning Techniques

Lessons 5-8: Regression Analysis

  • Lesson 5: Introduction to Linear Regression
  • Lesson 6: Predicting North American Pumpkin Prices (Linear Regression)
  • Lesson 7: Predicting Pumpkin Prices (Polynomial Regression)
  • Lesson 8: Introduction to Logistic Regression

Lesson 9: Web Application Development

  • Lesson 9: Building Web Applications

Lessons 10-13: Classification Algorithms

  • Lesson 10: Introduction to Classification Algorithms
  • Lesson 11: Classifying Asian and Indian Cuisine
  • Lesson 12: More Classification Algorithms
  • Lesson 13: Recommendation Systems

Lessons 14-15: Clustering Algorithms

  • Lesson 14: Introduction to Clustering Algorithms
  • Lesson 15: Exploring Nigerian Music Taste

Lessons 16-20: Natural Language Processing

  • Lesson 16: Introduction to Natural Language Processing
  • Lesson 17: Common NLP Tasks
  • Lesson 18: Translation and Sentiment Analysis
  • Lesson 19: Analyzing Romantic Hotel Reviews (1)
  • Lesson 20: Analyzing Romantic Hotel Reviews (2)

Lessons 21-23: Time Series Analysis

  • Lesson 21: Introduction to Time Series Forecasting
  • Lesson 22: ARIMA Time Series Forecasting
  • Lesson 23: Support Vector Regression Time Series Forecasting

Lessons 24-25: Reinforcement Learning

  • Lesson 24: Reinforcement Learning and Q-Learning
  • Lesson 25: Reinforcement Learning with Gym

Lesson 26: Real-World Applications

  • Lesson 26: Machine Learning Applications in the Real World

Tech Stack and Tools

Main Programming Languages

  • Python: Primarily using Python for teaching
  • R: Some lessons provide R language versions

Core Libraries and Frameworks

  • Scikit-learn: Main machine learning library
  • Python Data Science Ecosystem: pandas, numpy, matplotlib, etc.

Supporting Tools

  • Jupyter Notebook: Interactive programming environment
  • R Markdown: Used for R language courses
  • Quiz App: Dedicated quiz application

Learning Resources

Multimedia Support

  • Sketchnotes to help understand concepts
  • Video tutorials for supplementary explanations
  • Demonstrations of practical projects

Assessment System

  • 52 quizzes (each containing 3 questions)
  • Pre-lesson warm-up quizzes
  • Post-lesson consolidation quizzes
  • Project practice assessments

Community Support

  • GitHub Discussions
  • Learning Progress Tracker (PAT)
  • Peer learning and feedback

Learning Recommendations

Target Audience

  • Machine learning beginners
  • Learners with basic programming experience
  • Individuals who want to systematically learn classic machine learning

Learning Methods

  1. Fork the project to your personal GitHub account
  2. Complete each lesson in order
  3. Complete all practical projects
  4. Participate in community discussions and peer learning

Companion Courses

Project Team

Main Authors

  • Jen Looper, Stephen Howell, Francesca Lazzeri
  • Tomomi Imura, Cassie Breviu, Dmitry Soshnikov
  • Chris Noring, Anirban Mukherjee, Ornella Altunyan
  • Ruth Yakubu, Amy Boyd

Illustration Design

  • Tomomi Imura, Dasani Madipalli, Jen Looper

Student Ambassador Contributors

  • Rishit Dagli, Muhammad Sakib Khan Inan, Rohan Raj
  • Alexandru Petrescu, Abhishek Jaiswal, Nawrin Tabassum
  • Ioan Samuila, Snigdha Agarwal

Usage

Get the Project

git clone https://github.com/microsoft/ML-For-Beginners.git

Run Documentation Locally

npm i docsify-cli -g
docsify serve

Access Online

  • Directly access the GitHub repository
  • View the Microsoft Learn collection
  • Watch YouTube video tutorials

License and Contribution

The project follows an open-source license and welcomes community contributions. The project provides detailed contribution guidelines and code of conduct, supporting multilingual translation and content improvement.