CS 480
Introduction to Machine Learning
Winter 2026
Topics
- Supervised, unsupervised and reinforcement learning
- Bias-variance, overfitting and dimensionality
- Linear and logistic regression
- Nearest neighbours, trees and boosted predictors
- Gradient descent and stochastic gradient descent
- Regularization, sparsity, support vector machines and kernels
- Neural networks and convolution
- Autoencoders and generative models
- Attention, transformers and large language models
- Clustering, mixtures, EM and principal components
- Adversarial learning
- Privacy, fairness and interpretability
Readings
- The Elements of Statistical Learning
- Learning Theory from First Principles
- Machine Learning: A Probabilistic ApproachTitle as written on the course resource page; edition reference is ambiguous.
- Dive into Deep Learning
- Deep Learning
- All of Statistics
- Introduction to Graph Theory
- Introduction to Algorithms
- Convex Optimization
- Numerical Recipes
- Elements of Information Theory
2016
Topics
- Introduction
- Linear models
- Non-linear models
- Unsupervised learning
- Sequence learning
- Ensemble learning
- Large scale learning
- End user issues of Machine Learning
- Real-world applications of Machine Learning
- Topics in Machine Learning
Readings
- A course in Machine Learning
- Deep Learning
- Pattern Recognition and Machine Learning
- Machine Learning, A Probabilistic Perspective
Sources
- Course catalogue ↗2026–2027
- course_website ↗Winter 2026
- departmental_course_outline ↗2016
- Tentative syllabus; some advanced topics are optional.
- Departmental typical outline and references; assignments and textbooks may vary by term. Source revision: June 2016. Year refers to the departmental revision date, not a specific offering.