Tentative Schedule
Date | Topic | Materials | Homework |
Jan. 7 | Course overview. What is AI? Brief history. | Lecture 1 slides RN, 3rd or 2nd ed. Chapter 1, 2 Turing's 1950 paper ALICE the chatbot Julia the chatbot Video of Claude Shannon's juggling robot DARPA grand challenge and Urban challenge Deep Blue Polaris, the poker-playing program Tom Mitchell's mind reading project | |
Jan. 9 | Search | Lecture 2 slides RN, 3rd ed. Sec. 3.1-3.3 or RN 2nd ed. Sec. 3.1-3.5 Uninformed search applets Graph search tool |
Jan.14 | Search | Lecture 3 slides RN, 3rd ed. Sec. 3.5-3.6 or RN 2nd ed. Sec. 4.1-4.2 Paper on real-time A* Applet for visualizing different search algorithms |
Homework 1 posted |
Jan.16 | Search | Lecture 4 slides RN, 3rd ed. Sec. 4.1-4.2 or RN 2nd ed. Sec. 4.3-4.4 Travelling salesman problem An applet for TSP using simulated annealing |
|
Jan.21 | Genetic algorithms. Constraint satisfaction problems. | Lecture 5 slides RN, 3rd ed. Chapter 6 or 2nd ed.Chapter 5 TSP using genetic algorithms CSP solver demo CSP solver using stochastic local search N-queens demo |
|
Jan.23 | Game playing. Adversarial search | Lecture 6 slides RN, 3rd ed. Sec. 5.1-5.4 or 2nd ed. Sec. 6.1-6.4 Deep Blue Samuel's early checkers player Schaeffer et al. checkers solution Logistello |
Package to generate random mazes and test program |
Jan.28 | Game playing. Adversarial search | Lecture 7 slides Readings to come |
Homework 1 (written questions) due |
Jan.30 | Logic and planning | Lecture 8 slides RN, 3rd or 2nd ed. Sec. 8.1-8.3, 9.1-9.5 A Wumpus world demo Another Wumpus world, with different kinds of agents |
Homework 1 programming due |
Feb. 4 | Logic and planning | Lecture 9 slides |
Homework 2 posted |
Feb. 6 | Representing uncertainty. Probabilities and conditional probabilities. Bayes rule | Lecture 10 slides RN, 3rd or 2nd ed. Chapter 13 Bayes rule applet |
|
Feb.11 | No class | ||
Feb.13 | Bayes nets (representation, examples, inference) | Lecture 11 (done on the board, typed notes to be posted) |
Homework 2 due |
Feb.18 | Guest lecture: Prof. Greg Dudek | Lecture 12 | |
Feb.20 | Guest lecture: Prof. Joe Vybihal | Lecture 13 | |
Feb.25 | Making decisions under uncertainy: Utilities. Decision graphs. Introduction to bandit problems | Lecture 14 | |
Feb.27 | In-class midterm examination | Covering lectures up to and including February 6 Midterm from 2010 and solutions More example questions and solutions You are allowed one double-sided cheat sheet. |
|
Mar. 4 | Spring break | ||
Mar. 6 | Spring break | ||
Mar.11 | Bandit problems: Exploration vs exploitation trade-off. Sequential decision making. Markov chains. Markov Decision Processes. | Lecture 15 slides | Homework 3 posted |
Mar.13 | More on MDPs. Policies and value functions. Dynamic programming | Lecture 16 slides |
|
Mar.18 | More on MDPs. Introduction to reinforcement learning | Lecture 17 slides |
|
Mar.20 | Reinforcement learning (previous lecture) | Homework 3 due |
|
Mar.25 | More on learning. Linear function approximation. Gradient descent | Lecture 18 slides RN 3rd ed. or 2nd ed. Sec. 18.3 |
|
Mar.27 | Neural networks | Lecture 19 slides |
|
Apr. 1 | Easter Monday | ||
Apr. 3 | Wrap-up of neural nets. Clustering |
Lecture 20 slides |
|
Apr. 8 | Special topics: case studies of AI applied to games | Homework 4 posted | |
Apr.10 | Special topics: Natural language processing | Lecture 22 slides | |
Apr. 15 | Wrap-up: Philosophy and future of AI | Lecture 23 slides RN 3rd ed. or 2nd ed. Chapter 26, 27 Final exam from 2010 |
Homework 4 due; Project due (no penalties until April 22) |