 Topics  Lecture Notes  Reading  Problem Set  Solutions 
Mon. 3/31  Unsupervised vs. Supervised Learning; Clustering with kmeans and kmedoids  Lecture 1 Slides  ESL 14.1, 14.3 (except 14.3.7, 14.3.12) Optional: kmeans++, Gap statistic, kdtrees     
Weds. 4/2  Gaussian Mixture Models; ExpectationMaximization  Lecture 2 Scribed Notes Lecture 2 Slides  ESL 6.8, 8.5, 14.3.7 Mixture modeling chapter, EM chapter     
Mon. 4/7  ExpectationMaximization; General Mixture Modeling  Lecture 3 Scribed Notes  Mixture modeling chapter, EM chapter Optional: Original EM paper     
Weds. 4/9  Discrete Hidden Markov Models  Lecture 4 Slides Lecture 4 Scribed Notes  HMM chapter  Homework 1, Data  Homework 1 Solutions 
Mon. 4/14  Discrete HMMs; Hierarchical Clustering  Lecture 5 Scribed Notes  HMM chapter, ESL 14.3.12     
Weds. 4/16  Hierarchical Clustering; Spectral Clustering  Lecture 6 Scribed Notes Lecture 6 Slides  ESL 14.3.12, 14.5.3, Spectral clustering tutorial Optional: Minimax linkage     
Mon. 4/21  Spectral Clustering; Linear Dimensionality Reduction via Principal Component Analysis  Lecture 7 Slides Lecture 7 Scribed Notes  Spectral clustering tutorial, ESL 14.5.3, 14.5.1, 3.5.1 Optional: Normalized cuts     
Weds. 4/23  Principal Component Analysis; Kernel PCA  Lecture 8 Slides Lecture 8 Scribed Notes  ESL 14.5.1, 3.5.1, 14.5.4 Kernel PCA  Homework 2, Data  Homework 2 Solutions 
Mon. 4/28  Kernel PCA; Factor Analysis  Lecture 9 Slides Lecture 9 Scribed Notes  ESL 14.7.1, Multivariate Gaussian chapter, Factor analysis chapter     
Weds. 4/30  Factor Analysis; Linear Gaussian StateSpace Models and Kalman Filtering  Lecture 10 Scribed Notes  Factor analysis chapter, Statespace models chapter Optional: Probabilistic PCA     
Mon. 5/5  Linear Gaussian SSMs  Lecture 11 Scribed Notes  Statespace models chapter     
Weds. 5/7  SSMs; Independent Component Analysis; Canonical Correlation Analysis  Lecture 12 Slides Lecture 12 Scribed Notes  ESL 14.7, 3.7, ICA  Homework 3, Data  Homework 3 Solutions 
Mon. 5/12  CCA; Sparse Unsupervised Learning  Lecture 13 Scribed Notes  ESL 3.7, 14.5.5, Exact and greedy sparse PCA     
Weds. 5/14  Sparse Unsupervised Learning  Lecture 14 Scribed Notes Lecture 14 Slides  ESL 14.5.5, DSPCA Optional: Deflation methods, Sparse clustering  Practice Midterm Questions  Practice Midterm Solutions 
Mon. 5/19  Unsupervised Deep Learning  Lecture 15 Slides Lecture 15 Scribed Notes  Representation learning Optional: Deep learning     
Weds. 5/21  Inclass Midterm      Midterm  Midterm Solutions 
Mon. 5/26  Memorial Day  No Class         
Weds. 5/28  Learning with Missing Data  Lecture 16 Scribed Notes  ESL 9.6     
Mon. 6/2  Unsupervised Learning with Missing Data  Lecture 17 Scribed Notes  Matrix factorization, Nuclear norm heuristic Optional: Alternating minimization theory, Weighted trace norm     
Weds. 6/4  Final Project Presentations  Sequoia Hall Courtyard        
