Syllabus
CSCE 4613, Artificial Intelligence, Fall 2018

Description

Introduction to artificial intelligence. Covered topics include software agents, path search and planning, genetic algorithms, probabilistic reasoning, utility theory, and select machine learning models.


Prerequisites: CSCE 3193.

Text Book:

No text book. Some on-line reading materials will be assigned.

Grading:

2 or 3 exams are planned for this semester. All exams will be comprehensive.

Several (about 7) programming assignments are planned. All programming assignments must be completed by individual students. These assignments are challenging, and will require many hours of work outside of class. 8-12 hours per week is estimated, but significantly more time may be needed depending on programming proficiency. Assigned work may not be evenly distributed throughout the semester, so students should plan accordingly.

Each exam and assignment will be given a score from 0 to 100. The final score in the class will be computed with approximately the following weightings:

Exams: 40%
Assignments: 60%
However, a student's final score cannot exceed his or her average exam score by more than 15%. Also, a student's final score cannot exceed his or her average assignment score by more than 15%. In other words, the final score in the class will be computed as the lowest of three values:
  1. The weighted average score of exams and assignments,
  2. The average exam score plus 15%,
  3. The average assignment score plus 15%.

Final grades will be assigned according to where final scores fall within the following intervals:

A: [90%, 100%]
B: [80%, 90%)
C: [70%, 80%)
D: [60%, 70%)
F: [0%, 60%)

Late and incomplete work:

Each assignment will be given up to 60 points for completeness and up to 40 points for punctuality. Late submissions will have 3 points per day late deducted from the punctuality score. After two weeks (when the punctuality points run out), there will be no further penalty for lateness, however no work will be accepted after the last day of class. Incomplete work will not be accepted until after punctuality points run out. Before the punctuality points run out, if any part of an assignment submission has not been fully completed as required, the submission will be rejected, no points will be given, and students will need complete the assignment and resubmit. After the punctuality points run out, partial credit may be given if requested, but cannot exceed 60 points. It should also be noted that getting code to work is deemed to require significantly more effort than writing it in the first place. Thus, writing broken code does not entitle one to a large portion of the completeness points.

Every semester, someone experiences some sort of hardware failure. Students can adapt by working in the programming laboratories. They can prepare by making backup copies of their work on a thumb drive or Internet drive. They can also ask me to send to them copies of their previous submissions. So, hardware failures do not generally justify leniency. You have been warned.

Office hours:

Office hours are posted on the class web page. Office hours are for asking questions or seeking help, not for making you feel secure while you complete your programming projects. Please do your assignments away from the instructor and his assistants. Every 10 minutes or so, please return to the back of the line so that others may get help too. And while you are waiting, talk to each other. The instructor and his assistants are not the only people who know anything.

Academic Misconduct:

As a core part of its mission, the University of Arkansas provides students with the opportunity to further their educational goals through programs of study and research in an environment that promotes freedom of inquiry and academic responsibility. Accomplishing this mission is only possible when intellectual honesty and individual integrity prevail. Each University of Arkansas student is required to be familiar with and abide by the University's `Academic Integrity Policy' at honesty.uark.edu. Students with questions about how these policies apply to a particular course or assignment should immediately contact their instructor.

Students are expected to learn all of the skills they demonstrate in the programming assignments, as opposed to performing them only once. Failure of a student to be able to explain or reproduce his or her own code is clear evidence of academic dishonesty in this class. If code is provided by the instructor to assist with assignments, unless otherwise explicitly stated, students must understand that code in order to use it.

I do not determine the penalties for any incidence of cheating. I submit evidence to honesty.uark.edu then follow whatever sanctions they instruct me to impose. Code and other project you submit will be archived and analyzed to detect plagiarism. All assignment submissions are expected to be unique implementations made entirely by individual students. Large blocks of identical code in regions you were expected to implement yourself, (or code that differs only in variable names and whitespace, for example), is evidence of cheating. Any use of assignments written by other students for this class will be considered cheating. Every semester I adjust my assignments. Turning in implementations that include superfluous solutions to requirements from previous semesters is also evidence of cheating.

Here are some additional examples to clarify what is and is not cheating in this class. Note that this list is not complete:

Not cheatingCheating
Use the Internet to learn more about programming.Use someone else's completed assignments to help you learn how to do your assignments.
Discuss assignments with classmates.Turn in code containing portions written by someone else, or developed as a group.
Use small (5 lines or less) snips of code with proper attribution.Rename variables or functions to disguise the origin of some code.
Reuse some code you wrote for a different purpose.Turn in code that you cannot reproduce upon request.
Guess on a test.Report results that you did not actually achieve.
Study in groups.Communicate during a test.
Find external resources to augment your learning.Utilize anything that gives you an unfair grade advantage.

ADA Statement:

If any member of the class has a documented disability and needs special accommodations, the instructor will work with the student to provide reasonable accommodation to ensure the student a fair opportunity to perform in this class. Please advise the instructor of the disability and the desired accommodations within the first week of the semester.

Attendance and Participation:

If the university is officially closed, class will not be held. When the university is open, you are expected to make a reasonable effort to attend class, but not if you do not feel that you can get to campus safely. Assignment due dates will be postponed in case of inclement weather.

Emergency procedures

Many types of emergencies can occur on campus; instructions for specific emergencies such as severe weather, active shooter, or fire can be found at emergency.uark.edu.

Severe Weather (Tornado Warning)

Follow the directions of the instructor or emergency personnel. Seek shelter in the basement or interior room or hallway on the lowest floor, putting as many walls as possible between you and the outside. If you are in a multi-story building, and you cannot get to the lowest floor, pick a hallway in the center of the building. Stay in the center of the room, away from exterior walls, windows, and doors.

Violence / Active Shooter (CADD)

CALL- 9-1-1
AVOID- If possible, self-evacuate to a safe area outside the building. Follow directions of police officers.
DENY- Barricade the door with desk, chairs, bookcases or any items. Move to a place inside the room where you are not visible. Turn off the lights and remain quiet. Remain there until told by police it's safe.
DEFEND- Use chairs, desks, cell phones or whatever is immediately available to distract and/or defend yourself and others from attack.