COMP 590-125 (Fall 2013) — Artificial Intelligence

Modern techniques in artificial intelligence and machine learning.

Organizational

Time: Tuesdays, Thursdays 9:30-10:45
Place: FB 007
Prerequisites: COMP 410, Linear algebra, programming (Java/Python/Matlab/R)
Useful but not required: Probability or Statistics,
Instructor: Vladimir Jojic (vjojic@cs.unc.edu)
Office hours: SN 319 TBA

Overview

Artificial intelligence techniques are now commonly employed in designing agents assisting us in myriad of tasks. These techniques are applied in areas such as robotics, computer vision, natural language processing, video game design, etc. The course will cover the traditional AI problems and techniques as well as the modern probabilistic approach with a particular focus on machine learning techniques.

Grading

• Lecture participation: 20%
• Homework assignments (5): 50%
• Midterm: 10%
• Final: 30%

Topics covered:

Traditional AI

1. Introduction and History of AI
2. Search
3. Logical Agents
4. First Order Logic and Inference
5. Planning

Probabilistic/Machine Learning

1. Bayesian Inference
2. Graphical Models
3. Supervised and Unsupervised Learning
4. Neural Networks/Deep Learning

Applications

Depending on interest we may cover additional subjects.

Textbook

1. "Artificial Intelligence: A Modern Approach," Russell S. and Norvig P.
2. Optional "Machine Learning: A Probabilistic Perspective," Murphy K.

Slides

Date	Topic	Slides	Readings	HW
1/10	Organizational	Lecture 1 [PPT]
1/15	Definitions and history of AI	Lecture 2 [PPT]	Chapter 1
1/17	Intelligent Agents	Lecture 3 [PPT]	Chapter 2
1/22	Search	Lecture 4 [PPT]	Chapter 3
1/24	Informed Search	Lecture 5 [PPT]	Chapter 4
1/29	Constraint Satisfaction Problems	Lecture 6 [PPT]	Chapter 6
1/31	Adversarial search	Lecture 7 [PPT]	Chapter 5	HW1, due 2/13
2/5	Game theory	Lecture 8 [PPT]	Chapter 17.5...
2/7	Propositional logic and inference	Lecture 9 [PPT]	Chapter 7
2/14	First order logic and Prolog	Lecture 10 [PPT]	Chapters 8,9
2/19	Uncertainty	Lecture 11 [PPT]	Chapter 13
2/21	Bayesian Networks	Lecture 12 [PPT]	Chapter 14
2/26	Likelihood and Optimization	Lecture 13 [PPT]
2/28	Likelihood and Optimization II	Lecture 14 [PPT]