Statistical Learning

Course content

1. 1Prediction and inferenceComing
2. 2The bias–variance trade-offComing
3. 3Resampling for model assessmentComing
4. 4Lasso, ridge and elastic netComing
5. 5Splines and generalized additive modelsComing
6. 6Classification trees and regression treesComing
7. 7Bagging and random forestsComing
8. 8BoostingComing
9. 9Support vector machinesComing
10. 10Neural networks for statisticiansComing
11. 11Unsupervised learningComing
12. 12Capstone: a prediction competitionComing

Requirements

• STAT-311 Linear Models
• STAT-265 Statistical Computing with R and Python

Recommended background. You can start any course at any time.

Description

Prediction from data with modern methods: regularization, trees, ensembles, support vector machines and model assessment.

Part of the Science stream, typically taken in year 4.