CSCI 446
Artificial Intelligence
Fall 2014

Montana Tech
Computer Science & Software Engineering

Schedule  |  Assignments  |  Resources  |  Course syllabus  |  Moodle

SCHEDULE

This page lists the dates of all the lectures with links to slides and examples from the lecture (if any). Readings are in the book Artificial Intelligence: A Modern Approach (3rd edition) by Russell and Norvig. To get the most out of lectures, skim the reading beforehand (or at least look at the pictures!). You may also want to print out the slides before lecture so you can write and highlight on them during lecture. After the lecture, go back and read the pages carefully and do the book exercises.

#DateTopicSlidesReadingLinks
0 Mon 8/25 Introduction to AI PDF Ch 1 Berkeley, Intro
1 Wed 8/27 Agents and State Spaces PDF Ch 2, Ch 3.1-3.2 Reflex agent acting optimally  Reflex agent acting badly Agent that replans
- Fri 8/29 Lab, P0: Unix/Python tutorial
- Mon 9/1 NO CLASS
2 Wed 9/3 Uninformed Search PDF Ch 3.3-3.4 Berkeley, Uninformed Search  DFS and BFS step-by-step  Empty, DFS  Empty, BFS  Water, DFS  Water, BFS  Shallow/deep, DFS  Shallow/deep, BFS  Shallow/deep, UCS 
3 Fri 9/5 Informed search PDF Ch 3.5 Berkeley, Informed Search  A* step-by-step  Empty, UCS  Empty, Greedy  Empty, A*  Pacman, UCS  Pacman, UCS  Pacman, UCS  Shallow/deep, Greedy  Shallow/deep, A* 
- Mon 9/8 Lab, P1: Search in Pacman
4 Wed 9/10 Constraint Satisfaction I PDF Ch 6.1 Berkeley, CSP I  Coloring, DFS  Coloring, backtracking 
5 Fri 9/12 Constraint Satisfaction II PDF Ch 6.2-6.3 Berkeley, CSP II  Simple graph, forward checking  Complex graph, forward checking  Complex graph, arc consistency 
6 Mon 9/15 Constraint Satisfaction III PDF Ch 6.4-6.5 Iterative improvement, n-queens  Iterative improvement, coloring 
7 Wed 9/17 Local Search, Adversarial Search PDF  PDF Ch 5.2-5.5 Berkeley, Adversarial + local search  Alpha-Beta step-by-step  Mystery Pacman  Pacman, grim  Pacman, lucky  Depth limited 2  Depth limited 10  Smart ghosts  Smart ghosts 2 
- Fri 9/19 NO CLASS
- Mon 9/22 Lab, P2: Multi-agent Pacman
8 Wed 9/25 Game Trees: Expectimax PDF Ch 5.2-5.5 Berkeley, Expectimax and Utilities  Minimax Pacman  Expectimax Pacman  Random ghost vs. minimax Pacman  Random ghost vs. expectimax Pacman  Adversarial ghost vs. minimax Pacman  Adversarial ghost vs. expectimax Pacman 
9 Fri 9/26 Utilities Ch 16.1-16.3
- Mon 9/29 Lab, P2: Multi-agent Pacman
10 Wed 10/1 Markov Decision Processes PDF Ch 17.1-17.3 Berkeley, MDPs  Gridworld intro 
11 Fri 10/3 Markov Decision Processes II PDF Berkeley, MDPs II
12 Mon 10/6 Markov Decision Processes III
13 Wed 10/8 Reinforcement Learning PDF Ch 21 Berkeley, Reinforcement Learning Q-Learning, gridworld  Q-Learning, crawler 
14 Fri 10/10 Reinforcement Learning II PDF Berkeley, Reinforcement Learning II Q-Learning, cliff  Q-Learning, manual bridge  Q-Learning, epsilon greedy crawler           
- Mon 10/13 Lab, P3: Reinforcement Learning
15 Wed 10/15 Reinforcement Learning III
- Fri 10/17 Review for midterm PDF
- Mon 10/20 NO CLASS
- Wed 10/22 Midterm part 1: Search, CSPs, Games, Expectimax
- Fri 10/24 Midterm part 2: Utilities, MDPs, Reinforcement Learning
- Mon 10/27 Going over midterm
16 Wed 10/29 Probability PDF Ch 13.1-5 Berkeley, Probability  Ghostbusters, no probability  Ghostbusters, with probability 
17 Fri 10/31 Probability II Berkeley, Probability (first 30m) 
18 Mon 11/3 Markov Models PDF Ch 15.2,5 Berkeley, Markov Models (43m onwards, bad audio)  Berkeley, Markov Models (first 28m, good audio, somewhat different slides)  Markov model, basic  Markov model, circular  Markov model, whirlpool 
19 Wed 11/5 Hidden Markov Models PDF Ch 15.2,5 Berkeley, HMMs (bad audio, matching slides)  Berkeley, HMMs (good audio, somewhat different slides)  HMM, Pacman, with beliefs  HMM, Pacman, no beliefs  HMM, ghostbusters, circular  Robot localization 
20 Fri 11/7 Particle Filters PDF Berkeley, Particle Filters (60m onwards)  Particle filter, moderate  Particle filter, one  Particle filter, huge  Global sonar  SLAM 
- Mon 11/10 Lab, P4: Ghostbusters
21 Wed 11/12 Applications of HMMs PDF Ch 15.2,6 Berkeley, speech recognition (51m onwards)  Berkeley, speech recognition (46m onwards) 
22 Fri 11/14 Bayes' Nets: Representation PDF Ch 14.1-2,4 Berkeley, Bayes' Nets: Representation 
23 Mon 11/17 Bayes' Nets: Independence PDF Ch 14.1-2,4 Berkeley, Bayes' Nets: Independence  Berkeley, D-separation 
24 Wed 11/19 Bayes' Nets: Independence / Inference PDF Ch 14.4 Berkeley, Bayes' Nets: Inference  Step-By-Step: Elimination of One Variable  Step-By-Step: Variable Elimination 
25 Fri 11/21 Bayes' Nets: Inference
- Mon 11/24 Lab, P4: Ghostbusters
- Wed 11/26 NO CLASS
- Fri 11/28 NO CLASS
26 Mon 12/1 Bayes' Nets: Sampling PDF Ch 14.4-5 Berkeley, Bayes' Nets: Sampling  Step-By-Step: Sampling  Step-By-Step: Gibbs' Sampling 
27 Wed 12/3 Applications: NLP, games PDF
- Fri 12/5 Lab, homework 7/8
- Mon 12/8 Review PDF
- Wed 12/17 Final exam, 8am-10am, CBB 105

Page last updated: December 18, 2014