CS 540 Section 1: Introduction to Artificial Intelligence
Fall 2017 

Lectures: M,W,F 8:50am - 9:40am, Noland 132 Instructor: Professor Jerry Zhu Office Hours (you can come to any one of us) Jerry Zhu: F 2-3pm, CS6391, 608-890-0129, jerryzhu@cs.wisc.edu (section 2 instructors:) Collin Engstrom: Tu 5:30-6:30pm, CS4384, engstrom@cs.wisc.edu Dan Griffin: Mon 4:00-5:00pm, CS4384, dgriffin5@wisc.edu Ross Kleiman: Wed 1:00-2:00pm, CS4384, rkleiman@cs.wisc.edu (TAs) Zhenyu Zhang: Mondays 1-2pm, CS 7370, zhenyu@cs.wisc.edu Wolong Yuan: Mondays 2-2:30 pm, CS 7394, wyuan@cs.wisc.edu Stephen Sheen: Tuesdays 12:00-12:30 pm, CS 1308, sheen2@wisc.edu Ziyun Zeng: Tuesdays 4-5pm, CS 4331, ziyun@cs.wisc.edu Abhanshu Gupta: Wednesdays 5:00~6:00 pm, CS 4394, abhanshu@cs.wisc.edu Kurtis Liu: Thursdays 8-9 am, CS 5384, kliu89@wisc.edu Tananun Songdechakraiwut: Thur 2:30 - 3:30pm, CS 7331, tananun@cs.wisc.edu Aiqing Huang: Thursdays 4:00-5:00 pm, CS 4395, aiqingh@cs.wisc.edu Shiqi Yang: Fridays 3:00-4:00 pm, CS 4394, sqyang@cs.wisc.edu Piazza combined sections 1+2 Canvas https://canvas.wisc.edu/courses/51965 Homeworks Examinations Tentative Topics (reading list) Introduction (Stanford One Hundred Year Study on Artificial Intelligence; optional: textbook ch 1, 2; AAAI) Search Uninformed search: Breadth-first search, uniform-cost search, depth-first search, iterative-deepening (slides, ch 3) Informed search: A* algorithm (slides, ch 3) Greedy and stochastic search: Hill-climbing, Simulated annealing, genetic algorithms (slides, 4.1) Game playing: Minimax, alpha-beta pruning (slides, 5.1 - 5.3) Mathematics for Data Science Probability and statistics basics (slides, 14.1, 14.2, 14.4, Introduction to Probability, Statistics, and Random Processes) Application: Natural language and statistics (notes, Stanford English Tokenizer) Linear algebra and Principal Component Analysis (PCA) (notes, matlab demo PCA.m with its data files vocabulary_stopword_removal.txt and WARC201709BOW.txt, Numerical Algorithms Ch 1, math crib sheet) Logic: Propositional (slides, 7.1, 7.3 - 7.5) and First Order (slides, FOL inference slides) Machine Learning Unsupervised Learning Clustering (slides, Z&G ch 1 [free access from UW IP addresses]) Dimension reduction (we did PCA already) Supervised Learning k-Nearest-Neighbor classifier (knn demo) Linear regression, logistic regression (notes) Neural networks and deep learning (Nature'15, Deep Learning book, slides, Convolutional neural nets, 18.7, hand notes on backprop) Reinforcement Learning (Sutton and Barto 2nd ed., 1.1-1.4, 3, 6.5, Qlearning.m) Prerequisite: (COMP SCI 300 or 367) and (MATH 211, 217, 221, or 275) Textbook: Artificial Intelligence: A Modern Approach, 3rd edition (blue) Stuart J. Russell and Peter Norvig. Prentice Hall, Englewook Cliffs, N.J., 2010 Grading: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 ~20% of class AB next ~20% B next ~20% BC next ~20% C next ~15% D next ~3% F next ~2%