Machine Learning I (UMONS, 2023-2024)

This is a repository to organize the teaching material for Machine Learning I, to be taught by Souhaib Ben Taieb.

Course links

• Moodle (for discussion forum, assignments)

Project

• Project statement

Content

• Week 1 (Feb. 5-9).

  • Lecture 1 (Feb. 5): Introduction to Machine Learning [slides (PDF)]

• Week 2 (Feb. 12-16).

  • Lecture 2 (Feb. 12): Review of probability and statistics
  • Lab 1 (Feb. 13): Exploratory Data Analysis (Tutorial, Exercises, Solutions)

• Week 3 (Feb. 19-23).

  • Lab 2 (Feb. 19): Review of probability and statistics (Exercises, Solutions)
  • Lecture 3 (Feb. 21): Review of probability and statistics

• Week 4 (Feb. 26 - Mar. 1).

  • Lecture 4 (Feb. 26): The supervised learning framework [slides (PDF)]
  • Lab 3 (Feb. 26) Introduction to regression and classification with Scikit-Learn (Exercises, Solutions)

• Week 5 (Mar. 4-8).

  • Lecture 5 (Mar. 4): The supervised learning framework (continued) + Optimal predictions [slides (PDF)]
  • Lecture 6 (Mar. 6): The bias/variance tradeoff [slides (PDF)] + The bootstrap [slides (PDF)]

• Week 6 (Mar. 11-15).

  • Lecture 7 (Mar. 11): Linear regression [slides (PDF)]
  • Lab 4 (Mar. 12) Model selection using scikit-learn (Exercises, Solutions)

• Week 7 (Mar. 18-22).

  • Lecture 8 (Mar. 18): Linear regression
  • Lab 5 (Mar. 20) Bias-variance tradeoff (Exercises, Solutions)

• Week 8 (Mar. 25-29).

  • Lecture 9 (Mar. 25): Linear classification [slides (PDF)]
  • Lab 6 (Mar. 26) The bootstrap (Exercises, Solutions)

Spring Break

• Week 9 (Apr. 15-19).

  • Lab 7 (Apr. 16) Linear regression (Exercises, Solutions)
  • Lab 8 (Apr. 17) Classification (Exercises, Solutions
  • Lecture 10 (Apr. 19): Tree-based methods [slides (PDF)]

• Week 10 (Apr. 22-26).

  • Lecture 11 (Apr. 23): Dimension reduction [slides (PDF)]
  • Lab 9 (Apr. 24): Classification theory (Exercises, Solutions)
  • Lab 10 (Apr. 26): Regularization (Exercises theory, Solutions theory, Exercises practice, Solutions practice)

• Week 11 (Apr. 29 - May 3).

  • Lab 11 (Apr. 30) Tree-based methods (theory) (Exercises, Solutions)

• Week 12 (May 6-10).

  • Lab 12 (May 6): Tree-based methods (practice) (Exercises, Solutions)
  • Lab 13 (May 7): Dimension reduction (Exercises theory, Solutions theory, Exercises practice, Solutions practice)
  • Lecture 12 (May 8): The perceptron
  • Lecture 13 (May 10): Neural Networks (3Blue1Brown) (Chapters 1 and 2)

• Week 13 (May 13-17).

  • Lecture 14 (May 14): Neural Networks (3Blue1Brown) (Chapters 3 and 4) + Revision
  • Lab 14 (May 15): Perceptron (Exercises, Solutions), backpropagation (Exercises, Solutions), and intro to PyTorch (Tutorial)
  • Project presentations (May 17)