CS540-2: Introduction to Artificial Intelligence
Spring 2014

**Lectures**: MWF 11:00am - 11:50am, Computer Science 1221
**Instructor**: Bryan R. Gibson, Graduate Student in Computer Sciences
Office: CS 3395
E-mail: bgibson@cs.wisc.edu
**Office Hours** (you can come to any one of us):
Bryan Gibson (instructor): Fridays 1-2pm or by appointment, CS 3395, bgibson@cs.wisc.edu
Chuck Dyer (instructor for other section): Monday, Wednesday 2-3pm, CS 6379, dyer@cs.wisc.edu
TA: Han Li, Friday 3-4, CS 1309, hanli@cs.wisc.edu
TA: Mohammed Ansari, Thursday 12-1, MSC 6795, ansari@cs.wisc.edu
TA: Lichao Yin, Wednesday 3-4, CS 5395, lichao@cs.wisc.edu
**Discussions via Piazza** (need a wisc.edu email address to sign up here)
**Homeworks**
**Exams**
**Handin and Grades via Moodle**
**Topics (Reading)**
Unit 0: Introduction (lecture notes, Russell and Norvig (RN) chs 1,2)
AI: history and today
Unit 1: Search
Uninformed Search: Breadth-first search, uniform-cost search, depth-first search, iterative-deepening (slides, RN ch 3)
Informed search: A* algorithm (slides,RN ch 3)
More search: Hill-climbing, Simulated annealing, genetic algorithms (slides(pg.15),GA slides,RN 4.1)
Game playing: Minimax, alpha-beta pruning (slides, RN 5.1-5.3)
Constraint Satisfaction Problems (slides)
Unit 2: Machine Learning (math review)
Intro to ML and Clustering (slides, Zhu and Goldberg (ZG) ch 1)
HAC (HAC applet by M. Matteucci)
k-means (k-means applet by M. Matteucci
Classification (continuing with ZG ch 1.3)
k-Nearest-Neighbor (slides (pg 21), knn demo)
Perceptrons & Neural Networks (slides, addl. slides, RN 18.6-18.7)
Support Vector Machines (slides, addl slides, RN 18.9, short tutorial, long tutorial, demo applet)
Decision trees (slides, addl slides, RN 18.1-18.3, Example)
Probability and Statistics Basics (slides, addl slides, RN 14.1, 14.2, 14.4)
Bayesian Networks (slides, addl slides, tutorial (pp 1-23), Bishop PRML 8.2 for D-separation)
Speech Recognition, Markov Models and HMMs (slides, E. Fosler-Lussier Markov Models and Hidden Markov Models: A Brief Tutorial)
Unit 3: Logic
Propositional Logic (slides)
First-Order Logic (slides)
**Prerequisite**: CS 367
**Textbook**:
Artificial Intelligence: A Modern Approach, **3rd edition** (blue cover, not green).
Stuart J. Russell and Peter Norvig. Prentice Hall, Englewook Cliffs, N.J., 2010
**Grading**:

- Midterm Exam: about 30%
- Final Exam: about 30%
- Homework Assignments (4 to 5): about 40%

Note: The distribution of CS540 final grades has been as follows.
This is an approximation, and changes from semester to semester.
The median student's course grade is usually a low B or high BC.
The percentiles refer to ranking based on the final weighted score.
A top ~25% of class
AB next ~15%
B next ~25%
BC next ~20%
C next ~10%
D next ~3%
F next ~2%