Tutorial and Review Materials

CS 277: Spring 2013

---

Classification Algorithms:

• Naive Bayes classifiers
  • Introduction to naive Bayes, by Tom Mitchell (sections 1 and 2 in particular)
    
    
• Logistic Regression classifiers
  • Notes on sparse gradient descent for logistic regression, by Charles Elkan
  • Tutorial on multivariate logistic regression, by Javier Movellan
  • Making logistic regression a core data mining tool, by Paul Komarek (detailed discussion of computational aspects of fitting logistic regression models) - and a shorter conference version
    
    
• Decision Tree classifiers
• Support Vector Machines
  • Tutorial paper on SVMs by Bennett and Campbell (sections 1 through 7 in particular)
  • Tutorial slides on SVM basics, by Jean-Phillipe Vert
  • SVMs with applications to text classification, chapter 15 from Introduction to Information Retrieval by Manning, Raghavan, and Schutze
    
    
• Applications
  • Video lecture on fraud detection by David Hand
  • Text classification using naive Bayes, chapter 13 from Introduction to Information Retrieval by Manning, Raghavan, and Schutze
  • Early paper (1998) on using naive Bayes models for spam email filtering

Regression Algorithms

• Multivariate Linear Regression
• Generalized Linear Models

 

Clustering Algorithms

• Clustering algorithms with applications to document clustering, chapter 16 from Introduction to Information Retrieval by Manning, Raghavan, and Schutze
• Hierarchical clustering, chapter 17 from Introduction to Information Retrieval by Manning, Raghavan, and Schutze
• Probablistic model-based (mixture) clustering - overview by Fraley and Raftery, Computer Journal, 1998

 

Dimension Reduction Methods

• Principal Components and SVD
  • Matrix decomposition and SVD with applications to text, chapter 18 from Introduction to Information Retrieval by Manning, Raghavan, and Schutze

Statistical Learning

• Notes on MCMC and Gibbs sampling, B. Walsh, MIT, 2004