Course offered online through Standford University closely following the text "An Introduction to Statistical Learning, with Applications in R" (James, Witten, Hastie, Tibshirani - Springer 2013). Taught by the text authors.
3.1 Simple Linear Regression
3.2 Multiple Linear Regression
3.3 Interaction Terms
3.4 Non-linear Transformations of the Predictors
3.5 Qualitative Predictors
3.6 Writing functions combining modeling and plotting.
4.1 Logistic Regression
4.2 Linear Discriminant Analysis
4.3 Quadratic Discriminant Analysis
4.4 K-Nearest Neighbors
5.1 The Validation Set Approach
5.2 Leave-One-Out Cross-Validation
5.3 k-Fold Cross-Validation
5.4 The Bootstrap
6.1 Best Subset Selection
6.2 Forward and Backward Step-wise Selection
6.3 Model Selection Using a Validation Set
6.4 Model Selection by Cross-Validation
6.5 Ridge Regression and the Lasso
7.1 Introduction
7.2 Polynomials
7.3 Polynomial logistic regression
7.4 Splines
7.5 Generalized Additive Models
8.1 Introduction
8.2 Random forests
8.3 Boosting
9.1 Introduction
9.2 Linear Support Vector Classifier
9.3 Non-linear Support Vector Machine.
10.1 Principal Components
10.2 k-means Clustering
10.3 Hierarchical Clustering
But of course, what really matters when learning online is not the certificate but how much work and thought one puts in to understanding the material. In this vein, I often referenced The Elements of Statistical Learning to dive deeper into topics of interest. If a topic in ISLR leaves you curious for more, ESLR is an excellent compliment.