CS714: Machine Learning
Winter 2012


Information
Syllabus
Assignments
Project

Tentative Syllabus

Day Topic Reading Optional Reading
1/04/12 Introduction B 1-2; HTF 1 The discipline of machine learning by T. Mitchell; Statistical modeling: The two cultures in Statistical Science, 16(3):199-231, 2001 by L. Breiman; Wald Lecture 2002: Machine learning by L. Breiman
1/09/12 Linear prediction B 3.1.1-2 Norms in A.1.2-3, Convex Optimization by Boyd and Vandenberghe
1/11/12 Generalized linear prediction HTF 5.1-2, 5.7, 5.9, 6.1-3
1/16/12 Martin Luther King Day, University closed
1/18/12 Regularization, neural networks B 3.1, 5; HTF 3.4, 5.4, 11 Lecture notes by David McAllester; Neural network at Wikipedia; The next generation of neural network, Video by Geoffrey Hinton
1/23/12 Learning theory: Bias-variance B 3.2; HTF 2.9, 7 Lecture notes by David McAllester; Neural networks and the bias/variance dilemma in Neural Computation by Geman, Bienenstock and Doursat
1/25/12 Automated complexity control HTF 7
1/30/12 Linear classification, support vector machines B 7.1.1-2; HTF 4.5, 12.1-3 Tutorial by Ron Meir; Excerpt from Vapnik's The Natural of Statistical Learning Theory; Support vector machines with applications; SVM at Wikipedia;
2/01/12 Duality HTF 4.5, 12.1-3 Chapter 5, Convex Optimization by Boyd and Vandenberghe; The entire regularization path for the support vector machine at NIPS 2004 by Hastie et al.
2/06/12 Kernels B 6.1-3; HTF 5.8, 6.1-2, 6.7 Lecture notes by David McAllester
2/08/12 Kernels; Multiclass prediction (skipped) B 7.1.3 On the algorithmic implementation of multiclass kernel-based vector machines in JMLR 2001 by Crammer and Singer
2/13/12 Learning theory: Uniform convergence, Vapnik-Chervonenkis dimension HTF 7.9 Lecture notes by Andew Ng; Lecture notes by David McAllester; VC dimension at Wikipedia; On the uniform convergence of relative frequencies of events to their probabilities by Vapnik and Chervonenkis, 1971
2/15/12 Combining classifiers, boosting B 14.3; HTF 10 Toy example, training error proof, overview and slides and video by Schapire; Lecture notes by David McAllester; Evidence contrary to the statistical view of boosting in JMLR 2008 by Mease and Wyner.
2/20/12 Probability models, Bayes decision theory B 1.5 II.B and IV.B, An Introduction to Signal Detection and Estimation, by V. Poor; Decision Theory at Wikipedia
2/22/12 Bayesian networks and Markov random fields B 8.1, 8.3; HTF 17 Graphical models; Bayesian networks; Markov random fields at Wikipedia
2/27/12 Maximum likelihood estimation B 9.2 Generative and discriminative classifiers: naive Bayes and logistic regression by Tom Mitchell
2/29/12 Expectation-Maximization algorithm B 9.2-4; HTF 8.5 Lecture notes, Lecture notes by Andew Ng; Lecture notes by David McAllester; EM algorithm at Wikipedia
3/05/12 Hidden Markov models B 13.1-3 HMM tutorial and examples by L. Rabiner; Lecture notes by David McAllester; HMM at Wikipedia
3/07/12 Structured prediction: conditional random fields CRF paper and video by John Lafferty; Lecture notes by David McAllester; Conditional random fields at Wikipedia
3/12/12 Structured prediction: max-margin Markov networks (skip) M3N paper and slides and video by Taskar et al; M3N tutorial by S. Lacoste-Julien
3/12/12 Challenges in statistical machine learning Challenges in statistical machine learning and video by J. Lafferty
3/14/11 Project presentation