CS 560: Artificial Intelligence
Lectures: Mon/Wed 10:10-11:25am, Rm SN 011
Course Webpage: http://tamaraberg.com/teaching/Fall_15/

Instructor: Tamara Berg  (tlberg -at- cs.unc.edu)
Office: FB 236
Credits: 3 units
Textbook: "Artificial Intelligence: A Modern Approach", Russell and Norvig (3rd edition).
TA: Ric Poirson (poirson -at- cs.unc.edu)

Office Hours (Tamara): Mon/Wed 11:25-12:25pm, FB 236
Office Hours (Ric): Tues/Thurs 4-5pm, SN 109

Topics will include:
  • AI, Concepts and history
  • Solving problems by searching
  • Game Theory
  • Probabilistic reasoning
  • Machine Learning
  • NLP
  • Vision
Artificial Intelligence (AI) is the science and engineering of producing intelligent agents that can behave rationally. This includes methods for sensing the environment, planning, and acting to achieve goals. This course provides an introduction to a broad range of techniques and applications of modern AI, from combinatorial search to probabilistic models and reasoning. The course will also provide an introduction to some sub-areas of AI, including natural language understanding, robotics, and computer vision.

Announcements

  • 8/8/15: Welcome to AI!
  • 8/24/15: I sent out a test email to the class mailing list. Contact me if you did not receive it.
  • 8/26/15: Assignment 1 is now online here.
  • 8/31/15: Made a small update to wording in Assignment 1, available here.
  • 9/9/15: Deadline for Assignment 1 extended to Sunday, 9/13/15, 11:59pm.
  • 9/10/15: Important modification to Assignment 1: For problem 3 your code need only run on the small and tricky cheese mazes, with medium and big as extra credit. modified write-up here.
  • 9/17/15: Assignment 2 has been posted: here
  • 10/14/15: Assignment 3 has been posted: here
  • 11/9/15: Assignment 4 has been posted: here


Schedule (subject to change):

DateTopicSlidesReadingsAssignments
Aug 19Intro to AIintro.pptxCh. 1-
Aug 24Agents and Searchsearch1.pptxCh. 2-
Aug 26Search (cont)search2.pptxCh. 3Assignment 1 - HW1 grades
Aug 31Constraint Satisfaction Problemscsp_intro.pptxCh. 6.1-
Sep 2CSPs IIcsp.pptxCh. 6.2-6.5-
Sep 7Labor Day (no class)---
Sep 9CSPs Examplescsp_examples.pptxInferring Temporal Order of Images from 3D Structure-
Sep 14Gamesgames.pptxCh 5.2-5.5-
Sep 16Utility & Markov Decision Processesutility_mdps.pptxCh 16.1-16.3, Ch 17.1-17.3Assignment 2 - HW2 grades
Sep 21MDPs (cont) & Reinforcement Learningrl1.pptxCh. 21-
Sep 23Reinforcement Learning (cont)rl2.pptx--
Sep 28Review/Exercises---
Sep 30Midterm 1--Midterm1 grade summary
Oct 5Probabilityprobability.pptxCh. 13.1-13.5-
Oct 7Bayes' Netsbayesnets1.pptxCh. 14-
Oct 12University Day (no class)---
Oct 14Bayes' Nets (cont)bayesnets2.pptx-Assignment 3 - HW3 grades
Oct 19HMMshmms.pptxCh. 15-
Oct 21Machine Learning Overviewlearning.pptxCh. 18.1-18.4, 18.8-
Oct 26Classification Iclassification1.pptx--
Oct 28Classification II classification2.pptxCh. 18.6-18.7-
Nov 2Review/Exercises---
Nov 4Midterm 2 --Miterm2 grade summary
Nov 9Classification IIIclassification3.pptxCh. 18.9-18.10 Assignment 4
Nov 11Computer Vision vision1.pptxCh. 24-
Nov 16Computer Vision (cont)vision2.pptx--
Nov 18Natural Language Processingnlpintro.pptxCh. 22-
Nov 23Vision & Language Researchwords_and_pictures.pptx--
Nov 25Thanksgiving (no class)---
Nov 30AI, fun examples & discussion of where it's going next--Show & Tell - Bring in your favorite AI example to show/demo for the class (and submit half page write-up)
Dec 2Review/Exercises ---
Dec 11Final Exam (8am)---


Grading:

Students will complete 4 homework assignments, 2 midterm exams, and a final exam as part of the course. Assignments may include written questions and/or programming questions. Programming can be completed in the language of your choice, but code must run on the classroom servers and instructions for running your program must be included with your submission for full credit. Students are required to know how to program before taking this course. Readings are also required and will also be assigned from the textbook or posted to the class webpage.

Assignments must be turned in electronically by 11:59pm on the listed due date. Students will be allowed 5 free homework late days of their choice over the semester (you don't need to ask ahead of time, just use them and we will keep track). After those are used late homeworks will be accepted up to 1 week late, with a 10% reduction in value per day late.

There may be some short in-class quizzes (loosely graded) counted toward participation credit.

Grading will consist of 45% assignments, 40% exams, 15% participation.

Honor Code:

Assignments are encouraged to be completed in groups of up to 3. All code and written responses should be original. To protect the integrity of the course, we will be actively checking for code plagiarism (both from current classmates and the internet). Exams will be closed book.

Prerequisites & Target Audience:

Programming experience and data structures (COMP 401 and 410) are required. Algorithms (COMP 550), basic calculus, and working familiarity with probability are also encouraged/desired. Come talk to me if you have any questions! This course is targeted toward computer science majors in their junior or senior year of study. Students with an interest in general AI or areas related to AI, e.g. Natural Language Processing, Machine Learning or Computer Vision are encouraged to sign up.


Disclaimer:
The professor reserves to right to make changes to the syllabus, including project due dates and test dates. These changes will be announced as early as possible.