CS343H: Honors Artificial Intelligence</a> -- Fall 2017

CS343H: Honors Artificial Intelligence -- Fall 2017


Instructor: Peter Stone
Department of Computer Sciences

Tuesday, Thursday 9:30-10:45am
GDC 2.216

Jump to the assignments page.
Jump to the resources page.
Programming projects: Search; Multiagent; RL; Bayes; Ghostbusters; classification;
Final Contest; Contest Results;

Please complete the midterm course evaluation survey.


Instructor Contact Information

office hour: Thursdays 11am-noon (please let me know in advance if you're coming) and by appointment
office: GDC 3.508
phone: 471-9796
fax: 471-8885
email: pstone@cs.utexas.edu

Teaching Assistants

Josiah Hanna
office hours: Tuesday 12-1pm, Wednesday 11am-noon
office: GDC 1.302 (Northside basement TA stations)
email: jphanna@cs.utexas.edu

Yinan Zhao
office hours: Monday 10-11am, Friday 12:30-1:30pm
office: GDC 1.302 (Northside basement TA stations)
email: alexzhao@cs.utexas.edu

Proctor

Rohan Ramchand
office hours: Tuesday 3:30-4:30pm
office: GDC Basement Lab
email: rohan@cs.utexas.edu

Prerequisites

Upper-division honors standing in CS.

Syllabus and Text

This page serves as the syllabus for this course.
The course textbook is Artificial Intelligence: A Modern Approach
By Russell and Norvig
Published by Pearson.
Note: You need the 3rd Edition (Blue cover).

Selected readings from this text will be assigned, possibly to be supplemented by relevant research papers.

Assignments

Reading, written, and programming assignments will be updated on the assignments page. The readings and exercises may change up until the Tuesday before they are due (1 week in advance).

Discussion Forum

While the Professor and the TA would be glad to answer any questions you have, you will frequently find your peers to be an equally important resource in this class.

Please subscribe to our class piazza page.

Objectives

There are three primary objectives for the course:

The course is designed to present a solid entry point to the field of artificial intelligence. It will provide the foundation to go on to take other upper division AI courses. For those students with interest, it could possibly lead to subsequent research opportunities.

Content

There is no generally accepted definition of "artificial intelligence." Some that have been proposed include:

This course provides a broad introduction to artificial intelligence. Topics include:

Course Requirements

Written responses to readings (5%):
Weekly readings will be posted on the class website on Tuesday to be due the following week. Associated with some of the readings will be questions that should be answered with concise, well-thought-out, coherent written responses by email to the instructor and the TA. The email should be in plain ascii text in the body of the email (not an attachment). Please use the subject line "class readings for [due date]". In many cases, no specific questions will be posted. In those cases, the responses should be free form. Credit will be based on evidence that you have done the readings carefully. Acceptable responses include (but are not limited to):
  • Insightful questions;
  • Clarification questions about ambiguities;
  • Comments about the relation of the reading to previous readings;
  • Critiques;
  • Thoughts on what you would like to learn about in more detail;
  • Possible extensions or related studies;
  • Thoughts on the reading's importance; and
  • Summaries of the most important things you learned.
  • These responses will be graded on a 10-point scale and graded mostly on coherence and evidence of careful thought (most questions will not have a ``right'' answer). Answers will be due by 5pm the night before the class the associated reading is due (Monday or Wednesday night). Responses received between then and 8am on the class day will be deducted 1 point (for a maximum score of 9). Responses received between then and 8am the following class day will be deducted 2 points (for a maximum score of 8). Responses received after that will be deducted 4 points (for a maximum score of 6).

    These deadlines are designed both to encourage you to do the readings before class and also to allow us to incorporate some of your responses into the class discussions.

    Class participation (10%):
    Students are expected to be present in class having completed the readings and participate actively in the discussions.

    Homework Exercises (20%):
    Throughout the semester, problem sets will be assigned and automatically graded through the edX system. You will receive instant feedback from the autograder and can retry each problem as many times as necessary. The goal of these problems is to get you comfortable with the material and prepared for the midterm and final.

    Programming assignments (25%):
    There will be a series of Python programming projects in which you will implement various AI algorithms. An autograder script will be provided for each project so that you can check your progress along the way and fix errors in your code. The first of these projects (P0: Tutorial) must be completed individually. All other projects may be completed in pairs or alone.

    Midterm (15%):
    A midterm exam will be given in class.

    Final (25%):
    A final exam will be given on December 18th from 2-5pm.

    Major Assignment Due Dates

    Assignment Date Assigned Date Due
    EdX Homework 1: Search 9-5 9-19
    EdX Homework 2: Constraint Satisfaction 9-19 9-26
    EdX Homework 3: Adverserial Search 9-26 10-3
    EdX Homework 4: Markov Decision Processes 10-3 10-10
    EdX Homework 5: Reinforcement Learning 10-10 10-17
    EdX Homework 6: Probability and Bayes Nets 10-17 10-31
    EdX Homework 7: Bayes Nets: Sampling, Decision Diagrams, VPI + HMMs, Particle Filtering 10-31 11-7
    EdX Homework 8: Naive Bayes and Perceptrons 11-7 11-14
    EdX Homework 9: Neural Networks, Optimization, and Deep Learning 11-14 11-28
    Project 0: Python Tutorial 8-31 9-5
    Project 1: Search 9-5 9-26
    Project 2: Multi-agents 9-26 10-10
    Project 3: Reinforcement Learning 10-10 11-2
    Project 4: Bayes Nets 11-2 11-9
    Project 5: Ghostbusters 11-9 11-21
    Project 6: Classification 11-21 12-7
    Contest: Capture the Flag 10-31 12-5

    Extension Policy

    If you turn in your assignment late, expect points to be deducted. No exceptions will be made for the written responses to readings-based questions (subject to the ``notice about missed work due to religious holy days'' below). For other assignments, extensions will be considered on a case-by-case basis, but in most cases they will not be granted.

    For the penalties on responses to the readings see above (under course requirements). For other assignments, by default, 5 points (out of 100) will be deducted for lateness, plus an additional 1 point for every 24-hour period beyond 2 that the assignment is late. For example, an assignment due at 12:30pm on Tuesday will have 5 points deducted if it is turned in late but before 12:30pm on Thursday. It will have 6 points deducted if it is turned in by 12:30pm Friday, etc.

    The greater the advance notice of a need for an extension, the greater the likelihood of leniency.

    Academic Dishonesty Policy

    You are encouraged to discuss the readings and concepts with classmates. But all written work must be your own. And programming assignments must be your own except for 2-person teams when teams are authorized. All work ideas, quotes, and code fragments that originate from elsewhere must be cited according to standard academic practice. Students caught cheating will automatically fail the course. If in doubt, look at the departmental guidelines and/or ask.

    Notice about students with disabilities

    The University of Texas at Austin provides upon request appropriate academic accommodations for qualified students with disabilities. To determine if you qualify, please contact the Dean of Students at 471-6529; 471-4641 TTY. If they certify your needs, I will work with you to make appropriate arrangements.

    Notice about missed work due to religious holy days

    A student who misses an examination, work assignment, or other project due to the observance of a religious holy day will be given an opportunity to complete the work missed within a reasonable time after the absence, provided that he or she has properly notified the instructor. It is the policy of the University of Texas at Austin that the student must notify the instructor at least fourteen days prior to the classes scheduled on dates he or she will be absent to observe a religious holy day. For religious holy days that fall within the first two weeks of the semester, the notice should be given on the first day of the semester. The student will not be penalized for these excused absences, but the instructor may appropriately respond if the student fails to complete satisfactorily the missed assignment or examination within a reasonable time after the excused absence.

    Slides

    Slides from the classes as well as other resources are posted on the class resources page.

    Relevant Links

  • Some previous versions of this course at UT
  • Similar courses elsewhere
    • Berkeley: Stuart Russell - 2014
    • Berkeley: Pieter Abbeel and Dan Klein - 2014
      Much of the course material is based closely on the Berkeley course. The link above includes many useful lecture videos and supplementary tutorial videos
  • A course taught by me on autonomous multiagent systems

  • [Back to Department Homepage]

    Page maintained by Peter Stone
    Questions? Send me mail