CS 827 - Artificial Intelligence

Unit 1	Logic and Planning	Assignment: read chapters 8-11 in the text. Do the following exercises: chapter 8: 8.17, 8.18, 8.19, 8.23 chapter 9: 9.4, 9.22, 9.23 chapter 10: 10.3, 10.13 chapter 11: 11.2, 11.7 Lecture Notes for chapter 8. Lecture Notes for chapter 9. Lecture Notes for chapters 10 and 11. Here is the page for the FF planner, and a paper on the planner. You can download and install the planner on your computer, or you can download a virtual machine with FF installed and run it. To use the virtual machine you need VMWare. You can install the free VMPlayer. The password for logging into the VM is "learn". Here is the page for the FF planning domains. You can run the planner on the Hanoi domain, and also on some small examples of the Logistics domain, systematically varying the parameters and recording the times. Each domain has a problem generator that creates problems that the planner can run. Follow these instructions to run the planner. And here is a page of links to info about the planning competitions. CPM scheduling Video lectures on Logic. Video lecture on Planning. Here is a paper on robot planning, and here is a book on planning algorithms. Here is the video of class January 22. Here is the video of class January 24 from last year. Here is the video of class January 29 from last year. Here is the video of class Febuary 5 from last year. Here are the notes for class February 7 from last year.
Unit 2	Reasoning with Uncertainty	Assignment: Read chapters 14,15.1-15.4,16.1-16.4,17.1-17.4 in the text. Chapter 13 provides background. Do the following exercises: chapter 14: 14.1, 14.4, 14.11 a-d chapter 15: 15.2, 15.13 chapter 17: 17.1, 17.2, 17.13 Lecture Notes part 1 and part 2 for chapter 14. Bayes Network Visualization Paper Bayes Network Repository video on Random Walks Lecture Notes part 1 and part 2 for chapter 15. Markov Model Notes Lecture Notes for chapter 16. Lecture Notes for chapter 17. Value Iteration Lecture Notes Policy Iteration Lecture Notes A Lecture on Probability: Video (start about 8:30 into the video) Two Lectures on Markov Models: Video 1 and Video 2 Two Lectures on Markov Decision Processes: Video 1 and Video 2 Three Lectures on Bayesian Inference: Video 1 and Video 2 and Video 3 Here are the notes for class February 21. Here are the notes for class February 26. Here are the notes for class February 28. Here are the notes and the video from last year for the class on February 28.
Unit 3	Learning	Assignment: Read chapter 19.1-19.3 in the text and do these homework problems . Lecture Notes for chapter 19. Mitchell textbook
Unit 4	Learning Probabilistic Models	Assignment: Read chapter 20 in the text. Learning notes Logistic Regression notes Neural networks notes EM algorithm video
Unit 5	Independent unit: Reinforcement Learning	Assignment: Read chapter 21 in the text. This material will not be covered in class, but will be on the exam. You must learn this material independently. Video lecture on Reinforcement Learning. Two Other Lectures on Reinforcement Learning: Video 1 and Video 2
	Qualifying Exam	Some papers illustrating the application of concepts from the course: Path planning HMM Q learning Deep Q learning Assignment: Study! 4/1 - No class, do Chapter 21. 4/3 - Class - finish chapter 19, start chapter 20. 4/8 - Class - finish chapter 20. 4/10 - No class, do Chapter 21 and projects 4/15 - review session, ask questions & email practice exam 1 Practice Qualifying Exam #1 Practice Qualifying Exam #1 Key 4/17 & 4/22 - No class 4/24 - answers to practice exam 1, email exam 2 Practice Qualifying Exam #2 Practice Qualifying Exam #2 Key 4/29 - No class, study. 5/1 - in-class practice exam 1:20pm - 4:20pm Practice Qualifying Exam #3 Practice Qualifying Exam #3 Key 5/6 - cover answers for practice exams & review Wednesday 5/8 - Qualifying exam 1:20pm - 4:20pm