COMPSCI 4AL3

Applied Machine Learning at McMaster University.

Applied Machine Learning

Fall 2025

Overview: Machine learning has been critical in the field of artificial intelligence, which has seen an explosion in popularity in recent years. It refers to a set of statistical tools used to solve a wide array of learning problems. This course focuses on the application, practical use, and ethical considerations of machine learning models and learning methodologies. You will learn how to formulate problems, gather data, train and evaluate models, taking design considerations into account. This course will cover important theoretical concepts but will not go in-depth into machine learning theory.

Topics include how to train and evaluate models, supervised learning, unsupervised learning, reinforcement learning, linear models, neural networks, crowdsourcing, bias and fairness, explainability, generative models. Assignments and lectures will focus on the Python language and will require programming background. Practices and developments will be discussed with practical exercises.

Books: The following books will be used for course readings. These are available online through e-reserves. You can access them on Avenue under the e-reserves module.

  1. Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani, and Jonathan Taylor. Introduction to Statistical learning.
  2. Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong. Mathematics for Machine Learning.
  3. Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep Learning.

Tentative Schedule: The lectures for the course cover the following topics. This is subject to change

  • W1: Introduction to ML and supervised learning
  • W2: Training and evaluating ML models
  • W3: Regression, classification, and ranking problems
  • W4: Neural networks
  • W5: Crowdsourcing and Human-interaction
  • W6: Measuring algorithmic bias & fairness
  • W7: Unstructured data & unsupervised learning
  • W8: Recurrent & convolutional neural networks
  • W9: Attention, transformers, & generative AI
  • W10: Visualization, interpretability, & explainability
  • W11: Reinforcement & active learning
  • W12: Recent developments in ML\AI

Course Work and Grading: Your grade will be comprised of the following.

  • Four programming assignments
  • Class project - 3 stages
  • Midterm and final quizzes (2)