Machine Learning

CS760, Fall 2017
Department of Computer Sciences
University of Wisconsin–Madison


Important Notes

This schedule is tentative and subject to change. Please check back often.

How to interpret the column Readings in the Tentative Schedule

The reading is not required but strongly recommended for all students. Those explicitely noted as optional are for students interested in that specific topic. "A, B; C; D" means to read (A OR B) AND C AND D. Text in red means a link to the reading material. Abbreviations for textbooks:

Tentative Schedule

Date Lecture Readings Homework Released Homework Due
Wed, Sep 6 course overview [Slides] Homework 1 (background test)
Fri, Sep 8 machine learning overview [Slides] Mitchell chapter 1, Murphy chapter 1;
Dietterich, Nature Encyclopedia of Cognitive Science, 2003;
Jordan and Mitchell, Science, 2015
Mon, Sep 11 decision tree learning part 1 [Slides] Mitchell chapter 3, Murphy chapter 16.2, Shalev-Shwartz and Ben-David chapter 18
Wed, Sep 13 decision tree learning part 2 [Slides] Optional papers to read:
1. CART paper: Breiman, Leo; Friedman, J. H.; Olshen, R. A.; Stone, C. J. (1984). Classification and regression trees. Monterey, CA: Wadsworth & Brooks/Cole Advanced Books & Software. ISBN 978-0-412-04841-8.
2. ID3 paper: Quinlan, J. R. 1986. Induction of Decision Trees. Mach. Learn. 1, 1 (Mar. 1986), 81–106
3. C4.5 paper: Quinlan, J. R. C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers, 1993.
Fri, Sep 15 instance-based methods [Slides] Mitchell chapter 8, Shalev-Shwartz and Ben-David chapter 19
Mon, Sep 18 evaluating learning algorithms part 1 [Slides] Mitchell chapter 5, Murphy 5.7.2, 6.5.3;
Manning et al., Sections 8.3-8.4
Wed, Sep 20 evaluating learning algorithms part 2 [Slides] Homework 1 due
Fri, Sep 22 no class
Mon, Sep 25 Naive Bayes [Slides] Mitchell 6.1-6.10, Murphy 3
Wed, Sep 27 regression (linear and losgistic) [Slides] Murphy 8.1-3 and 8.6;
Maximum Likelihood, Logistic Regression, and Stochastic Gradient Training
Fri, Sep 29 neural networks part 1 [Slides] Mitchell chapter 4, Murphy 16.5 and 28, Bishop 5.1-5.3, Goodfellow-Bengio-Courville 6;
LeCun et al., Nature, 2015
Homework 2
Mon, Oct 2 neural networks part 2 [Slides] Mohri-Rostamizadeh-Talwalkar Appendix B (Convex Optimization), Bishop Appendix E (Lagrange Multipliers);
Goodfellow-Bengio-Courville chapter 7 and 8
Wed, Oct 4 neural networks part 3 [Slides] Goodfellow-Bengio-Courville chapter 9;
Optional papers to read:
1. LeNet
2. AlexNet
3. ResNet
Fri, Oct 6 neural networks part 4 [Slides] Goodfellow-Bengio-Courville chapter 10;
Optional papers to read:
1. LSTM
2. GRU
Mon, Oct 9 neural networks part 5 [Slides] Optional papers to read:
1. Deep Boltzmann Machines (DBM)
2. Generative Adversarial Networks (GAN)
Wed, Oct 11 learning theory part 1: PAC model [Slides] Mohri-Rostamizadeh-Talwalkar Chapter 2, Mitchell chapter 7
Fri, Oct 13 learning theory part 2: mistake-bound model [Slides] Optional paper to read:
1. Littlestone, N.; Warmuth, M. (1994). The Weighted Majority Algorithm. Information and Computation.
Homework 3 Homework 2 due
Mon, Oct 16 learning theory part 3: bias-variance decomposition [Slides] Geman et al., Neural Computation, 1992 (Sections 1-3)
Wed, Oct 18 Bayesian networks part 1 [Slides] Mitchell chapter 6, Bishop chapter 8.1, Shalev-Shwartz and Ben-David chapter 24
Fri, Oct 20 Bayesian networks part 2 [Slides] Heckerman Tutorial
Mon, Oct 23 Bayesian networks part 3 [Slides] Optional paper to read:
1. TAN algorithm (Friedman et al., Machine Learning, 1997)
2. Sparse Candidate algorithm (Friedman, Nachman, and Peer, UAI, 1999)
Wed, Oct 25 discriminative vs. generative learning
Fri, Oct 27 support vector machines part 1 Homework 3 due
Mon, Oct 30 support vector machines part 2
Wed, Nov 1 ensemble methods
Fri, Nov 3 feature selection
Mon, Nov 6 dimension reduction
Wed, Nov 8 reinforcement learning part 1
Fri, Nov 10 reinforcement learning part 2
Mon, Nov 13 machine learning in practice
Wed, Nov 15 active learning and semi-supervised learning
Dec 15-Dec 21 exam days