reset password

Welcome to Artificial Intelligence!

Syllabus, Fall 2014

Time: 9:10-1pm Saturday

Instructor: Mark Sargent, PhD

Contact Info: marke(nospamformeplease)sargent@gmail.com (Also write to forum).

Office Hours:  M 2:30 to 3:30 either in E&T A225, or the Graphics Communications A2A (Get off elevator on lowest floor, look to the door on your right, enter there and navigate until you see me). 

Introduction: This course is first of a two course series I will be teaching on artificial intelligence. This covers search, game trees, Markov decision processes, Bayes's Nets. The second (CS 454) covers probabilistic reasoning and machine learning. 

Prerequisites: CS 312

Recommended Background: Experience with Python would be helpful, but not required. 

Student Learning Outcomes:

SLO #1. Students will be able to apply concepts and techniques from computing and mathematics to both theoretical and practical problems.

SLO #2. Students will be able to demonstrate fluency in at least one programming language and acquaintance with at least three more.

SLO #3. Students will have a strong foundation in the design, analysis, and application of many types of algorithms.

SLO #5. Students will have the training to analyze problems and identify and define the computing requirements appropriate to their solutions.

SLO #7. Students will be able to communicate effectively orally and in writing.

Text: Artificial Intelligence: A Modern Approach, by Stuart Russell and Peter Norvig, Edition 3, Prentice Hall, 2009.

Course Requirements: Pass

  • Weekly Quizzes (10%)
  • Labs/Programming Assignments (50%)
  • Midterm Exam: (20%)
  • Final Exam: (20%)

Grade Scale:

Your course percentage will be calculated as a weighted average. Your letter grade will be determined by where it falls in the following scale:

92 -100%: A, 87- 91%: A-, 82-86%: B+, 77 to 81%: B, 72-76%: B-, 67-72%: C+, 62-66%: C, 57-61%: C-, 52-56%: D+, 47-51%: D, 42-46%: D-, 41% and below: F

I won't give you a lower grade than what is posted here, but I may curve upward.

Attendance/Participation/Class Etiquette: You will not be penalized specifically for missing class (unless there is an exam on the day you miss), but there will be frequent in-class assignments for which you are responsible. When in class:

  1. Leave the classroom only if you really need to.

  2. Turn off cell phones, or turn them to vibrate.

  3. Don’t engage in private conversations.

  4. Don’t sleep.

  5. Don't distract other students.

Please be respectful to everyone in the class.

Make-ups: No make-ups on quizzes, in-class work, homework, or exams.

Exceptions to this rule only on written proof of medical emergency (requiring doctor's visit and/or hospitalization), family tragedy, or work conflict. The medical emergency must be such as to prevent your attendance. All make-ups are done during the final exam period. You must contact me within 3 business days after the due date of the assignment with your excuse. If you do not, you will not be able to make up the assignment.

Complaints about grades must be made via email to me within 3 days of receiving your grade.

Take responsibility for your own drops!!!! (Drops are your responsibility!).

Important Administrative Information:

Academic

Integrity

Cheating will not be tolerated. Cheating on any assignment or exam will be taken seriously. All parties involved will receive a grade of F for the course and are reported to the proper authorities.

ADA Statement

Reasonable accommodation will be provided to any student who is registered with the Office of Students with Disabilities and requests needed accommodation.

Resources: 

Final Study Guide

This class will be using a lot of the resources found at http://ai.berkeley.edu/home.html, the home page for Berkeley's AI course taught by Pieter Abbeel and Dan Klein. I will more or less follow the material on the first dozen videos. You may watch the videos yourself before class if you want, but I will also be covering the same material in class as well.  

Some short videos going through many of the topics in this class can be found in the edX Artificial Intelligence course, also taught by Pieter Abbeel and Dan Klein. There is also a Udacity course on artificial intelligence. Peter Norvig (one of the textbook authors) and Sebastian Thurn (famous in robotics and machine learning) made these videos. 

Programming Assignments: Programming assignments will be in Python.

Schedule (Approximate/Tentative):

Note, there may be a quiz on the previous week's material any given week.

Week 1: Introduction, orientation, getting started with Python.

Week 2: Uninformed Search (video)

Week 3: Informed Search

Week 4: Constraint Satisfaction (Lecture 4 video)

Week 5: Adversarial Search (Lecture 6 video)

Week 6: Game Trees: Expectimax (Lecture 7 video)

Week 7: Markov Decision Processes (Lecture 8 video)

Week 8: Probability (Lecture 12 video)

Week 9: Bayes's Nets See the video series starting here: https://www.youtube.com/watch?v=-8DyY8_IuA0, and https://www.youtube.com/watch?v=1fVWQ-iZqsw

Week 10: Game Day!

 

 

 

Note: This syllabus is subject to revision.

This page has been viewed 13229 times.