Skip to content

Although we are not directly following any textbook in particular, the background readings for many of the topics will come from: Murphy, Kevin P. Machine Learning: a Probabilistic Perspective. Cambridge, MA: MIT press, 2012. Below, we will denote this book using "KM".

Background: Introduction to Probability and Statistical Learning [+] Expand All[+]

Case Study I: Estimating Click Probabilities [+] Expand All[+]

Online learning : KM Sec. 8.5

Sketching and Hashing

Personalization via Multi-task Learning

Case Study II: Document Retrieval [+] Expand All[+]

Basic kNN, TF-IDF

Fast NN Search

Clustering: KM Sec. 25.1

Mixed Membership Models: KM Sec. 27.3

Advanced reading: KM Sec. 21.1-21.3

Case Study III: fMRI Prediction [+] Expand All[+]

Linear and logistic regression: KM Sec. 7.1-7.3,7.5, 8.1-8.3, 8.5

LASSO: KM Sec. 13.1, 13.3, 13.4

Zero-shot learning

Graphical LASSO: KM Sec. 26.7

Parallel learning

Case Study IV: Collaborative Filtering [+] Expand All[+]

Collaborative Filtering:

Matrix Factorization:

Cold-start Problem (zero-shot learning), Incorporating Features:

Parallel Learning with GraphLab:

Advanced reading (optional):