CMSC 173 · Syllabus

Machine Learning

Fundamentals of machine learning algorithms and applications

This syllabus is not final. It is a working outline and will change before the term settles — the topic sequence below is indicative, and grading, deadlines and course policies are still being finalised. Anything here may be revised and announced in class. Do not treat it as the official course document.

Topics by week

WeekTopic
1 Introduction to Machine Learning slides
2 Parameter Estimation slides
3 Linear Regression slides
4 Regularization slides
5 Exploratory Data Analysis slides
6 Model Selection slides
7 Cross Validation slides
8 PCA slides
9 Logistic Regression slides
10 Classification slides
11 Kernel Methods slides
12 Clustering slides
13 Neural Networks slides
14 Advanced Neural Networks slides

Labs

WeekLab
1 Welcome Lab: What You Already Have Colab
2 Parameter Estimation & the Bias–Variance Tradeoff Colab
3 Linear Regression: Gradient Descent from Scratch Colab
4 Regularization: Ridge, Lasso & Choosing Lambda Colab
5 Exploratory Data Analysis with pandas Colab
6 Model Selection & Evaluation: Metrics & ROC Colab
7 Cross-Validation & Hyperparameter Tuning Colab
8 PCA from Scratch: Eigenvectors & Scree Plots Colab
9 Logistic Regression from Scratch Colab
10 Classification: KNN, Naive Bayes & Decision Trees Colab
11 Kernel Methods & Support Vector Machines Colab
12 Clustering: K-Means from Scratch Colab
13 Neural Networks: A 2-Layer Net from Scratch Colab
14 Under the Hood of Modern AI: Convolution & Attention Colab

Assessment

Not finalised. The weighting of labs, project and any exams will be confirmed and announced before it affects any submitted work.

Course policies

Attendance, late work, academic integrity and use of AI tools are still being finalised for this term.

Where things live

Slides & materialsThis portal — they stay up all term
Course introductionWelcome deck
Lab notebooksnjpinton/cmsc173-labs
Submitting labsSign in with your student number, then upload from the lab page