Fall 2012
Machine Learning home page | Syllabus | Schedule/Readings | Project Assignments | Resources |
Date | Topics | Assigned Readings |
Thurs. 8/23 |
Course Introduction Intro. to Learning |
|
Tues. 8/28 |
Designing learning systems (No lecture slides, but see Mitchell's Ch. 1 slides for related material, especially slides 11-21.) |
Ch. 1 |
Thurs. 8/30 |
Neural Networks Introduction Perceptrons Gradient descent (No lecture slides, but see Mitchell's Ch. 4 slides for related material.) |
Ch. 4 of Mitchell "The Basic Ideas in Neural Networks", by Rumelhart et al., Communications of the ACM, 37(3): 87-92, 1994. |
Tues. 9/04 |
Neural Networks (con't.) Stochastic gradient descent Multi-layer feedforward neural networks |
Ch. 4 of Mitchell Handout: Notes on Neural Networks
|
Thurs. 9/06 |
Neural Networks (con't.) Back Propagation Convergence issues K-fold cross-validation |
Ch. 4. of Mitchell |
Tues. 9/11 | Neural Networks (con't.) Momentum Design and performance issues Exploring ANN design with Sharky Discussion of project #1 |
Ch. 4 of Mitchell |
Thurs. 9/13 | Neural Networks (con't.) Case studies
Evaluation of learning algorithms:
|
Case Studies: A case study of using artificial neural networks for classifying cause of death from verbal autopsy, International Journal of Epidemiology, 2001, 30:515-520.
Predicting Students' Academic Performance using Artificial Neural Networks: A Case Study of an Engineering Course, The Pacific Journal of Science and Technology, Vol. 9, No. 1, May-June 2008, pgs. 72-79. A case study on using neural networks to perform technical forecasting of forex, Neurocomputing, Vol. 24, pgs. 79-98, 2000. Mangerial applications of neural networks: The Case of Bank Failure Predictions, Management Sceince, Vol. 38, No. 7, July 1992, pgs. 926-947. |
Tues. 9/18 |
Tutorial on LaTex Genetic Algorithms Introduction Evolutionary programming example: GOLEM project for evolving robots (No lecture slides, but see Mitchell's Ch. 9 slides for related material.) |
Ch. 9.1-9.2 of Mitchell
|
Thurs. 9/20 | Genetic Algorithms Representation Crossover operators Selection/Fitness TSP example
|
Ch. 9.2-9.3 of Mitchell
|
Tues. 9/25 | Genetic Programming Introduction Example: Boolean 11-Multiplexer Generating initial population Dealing with "code bloat" |
Ch. 9.4-9.5 of Mitchell Extra handouts: excerpts from John Koza's Genetic Programming, parts of Ch. 6 (pgs. 79-94) and Ch. 7 (pgs. 147-187) |
Thurs. 9/27 | Genetic Programming Closure and Sufficiency Example: Blocks world Example: Santa Fe Ant |
Koza handouts from last class
|
Tues. 10/02 |
Genetic Programming Example: Symbolic regression Revisiting GOLEM example
Discussion of Project #2
|
Automatic design and manufacture of robotic lifeforms, Nature,
vol. 406, August 31, 2000, pg. 974-978.
|
Thurs. 10/04 |
Introduction to Reinforcement Learning
Markov Property |
Ch. 13.1 - 13.2 of Mitchell Ch. 1 of Sutton and Barto text on RL |
Tues. 10/09 | Guest lecture by TA; instructor on research travel
Reinforcement learning Examples: Maze, K-Armed Bandit, etc. Infinite horizon, finite horizon V and Q functions |
Ch. 13.3 of Mitchell Ch. 3, 6.5 of Sutton and Barto text on RL |
Thurs. 10/11 | Fall break, no class |
|
Tues. 10/16 |
Review of Project #1
Reinforcement learning |
Ch. 13.4 - 13.5 of Mitchell Ch. 6 and 7 of Sutton and Barto text on RL |
Thurs. 10/18 |
Reinforcement learning TD Learning Sarsa (lambda) Eligibility traces
Tutorial on Player/Stage
| Paper introducing Player Player/Stage Getting Started Guide (UTK-specific) Player/Stage Documentation (Public-domain website)
Mini-Assignment #1 Assigned (easy!!)
|
Tues. 10/23 |
Guest lecture by TA; instructor on research travel
Reinforcement learning (con't.) |
Ch. 11 of Sutton and Barto text on RL |
Thurs. 10/25 | UTK Engineer's Day (undergrad engineering students are dismissed if you need to be involved in Engr. Day activities) Exercise overseen by TA; instructor on research travel In-class ML design exercise (non-credit) |
|
Tues. 10/30 |
Introduction to Support Vector Machines (SVMs) |
Handout: pages 744-748 of Artificial Intelligence, 3rd edition, by Russell and Norvig, Prentice-Hall, 2010. |
Thurs. 11/01 | SVMs (con't.) Maximizing margin formulation Intro to convex optimization |
Handout: pages 73-87 of Knowledge Discovery with Support Vector Machines, by Lutz Hamel, John Wiley and Sons, Inc., 2009. |
Tues. 11/06 | SVMs (con't.) Intro to quadradic programming Intro to concepts of primal/dual SVM dual representation Nonlinear SVMs Kernels and the Kernel Trick |
Handout: pages 102-109 of Knowledge Discovery with Support Vector Machines, by Lutz Hamel, John Wiley and Sons, Inc., 2009. |
Thurs. 11/08 | SVMs (con't.) Soft margin classifiers Multi-Class Classification |
Handout: pages 185-202, 114-122 of Knowledge Discovery with Support Vector Machines, by Lutz Hamel, John Wiley and Sons, Inc., 2009. |
Tues. 11/13 |
AdaBoosting and connection to SVMs AdaBoosting with SVMs for unbalanced data |
Handout: A Short Introduction to Boosting, by Freund and Schapire Handout: AdaBoost with SVM-based component classifiers, by Li, Wang, and Sung
Handout: AdaBoost.M1 description, by Freund and Schapire |
Thurs. 11/15 | SVMs (con't.) Parameter selection using cross-validation and grid search Introduction to LIBSVM Discussion of Project #4 |
LIBSVM website Handout: A practical guide to support vector classification, by Hsu, et al. |
Tues. 11/20 | Combining learners -- e.g, bagging Stable/unstable learners Inductive bias No Free Lunch Theorem |
Background reading: A simple
algorithm for learning stable machines, by Andonova, et al. |
Thurs. 11/22 | Happy Thanksgiving! (no class) |
|
Tues. 11/27 |
Learning Theory Probably Approximately Correct Learning Sample complexity for finite hypothesis space |
Ch. 7-7.3 of Mitchell |
Thurs. 11/29 |
Learning Theory Probably Approximately Correct Learning (con't.) Sample complexity for infinite hypothesis space |
Ch. 7.4 of Mitchell |
Tues. 12/04 | (Last class; no final exam) Wrapup Course |
|