16 sessions · Fall 2026
Lectures
Course introduction and semester project
Course overview, learning objectives, semester project introduction, and workflow norms
AI tools in a machine-learning workflow
Using generative AI responsibly in data science and ML workflows
Foundations and preprocessing pipelines
Data cleaning, feature engineering, and scikit-learn pipelines
Linear models for prediction
Linear regression, penalised regression (ridge, lasso), and prediction
Classification methods
Logistic regression, k-nearest neighbors, and naive Bayes
Bias-variance tradeoff
Understanding overfitting, underfitting, and the bias-variance decomposition
Model selection and cross-validation
Cross-validation, hyperparameter tuning, and model comparison
Project showcase (optional)
Optional class session where students present their projects for peer ideas and instructor feedback
Unsupervised learning and PCA
Principal component analysis and dimensionality reduction
Ensemble methods
Decision trees, bagging, and random forests
Support vector machines
Support vector classifiers, kernels, and SVM for classification
Gradient boosting
Boosting, gradient boosting machines, and XGBoost
Clustering
K-means clustering, hierarchical clustering, and cluster evaluation
Neural networks
Introduction to neural networks as a bridge from classical ML
Project workshop
Hands-on project workshop with peer feedback and instructor guidance
Summing up and Q&A
Course synthesis, key takeaways, and open Q&A