Course Syllabus

CPSC5185U Artificial Intelligence, CRN: 20510Spring Semester 2014Class Meets: Mon, Wed 3:00-4:15 CCT 408

Instructor | Description | Learning Objectives |Resources | Topics and Schedule| Assessment | Policies|Help | Important Dates

Instructor information

Name: Dr. Shamim Khan

Office: Center for Commerce and Technology (CCT) Room 444

Office hours:

Mon, Wed, Fri: 10:00 AM–12:00 PM

Tue, Thu: 9:30 AM–11:30 AM

Contacting me: If you need to discuss something, which does not require a face-to-face meeting, please e-mail me. If you need to see me face-to-face but cannot meet during the scheduled office hours listed above, please e-mail or call me so we can make arrangements to meet in my office at a more convenient time.

E-mail: (CougarView e-mail preferred for course related communication)

Web: http://csc.columbusstate.edu/khan

Office Phone:706-507-8184; School Phone: 706-507 8170; School Fax: 706-565-3529

Description

This course covers the fundamentals of artificial intelligence and its application to problem solving. The emphasis is on popular AI methodologies used for developing software systems known as intelligent systems. This course involves practical work.

The pre-requisite for this course isCPSC 2108 Data Structures with a grade of "C" or better.

Learning objectives

After completing this course, you should be able to: / How the learning outcome will be assessed
  • Define artificial intelligence (AI) and state its goals
  • Describe the characteristics of intelligence
  • Name common (artificially)intelligent system methodologies and give examples of such systems
/
  • Classroom quizzes
  • Assignment

  • Demonstrate knowledge of the widely known techniques that allow a computer to learn from data
/
  • Classroom quizzes

  • Demonstrate understanding of the structure and operation of a rule-based expert system
  • Build a simple rule-based expert system using an expert system shell
/
  • Classroom quizzes
  • Assignment

  • Demonstrate understanding of fuzzy logic and fuzzy reasoning
  • Build a simple fuzzy rule-based expert system using MATLAB or a fuzzy system shell
/
  • Classroom quizzes
  • Assignment
  • Project

  • Demonstrate a basic understanding of evolution in nature, and how evolutionary computation methodologies are modeled on it
  • Demonstrate sufficient understanding of Genetic Algorithms (GA) by developing a GA-based solution to a problem
/
  • Classroom quizzes
  • Assignment
  • Project

  • Demonstrate understanding of the artificial neuron and the Artificial Neural Network (ANN) as a simple model of the biological neuron and neuronal networks
  • Demonstrate understanding of machine learning through supervised and unsupervised training of ANNs
  • Build a simple ANN system using MATLAB or an ANN development environment
/
  • Classroom quizzes
  • Assignment
  • Project

  • Demonstrate a basic understanding of common knowledge representation schemes and how knowledge can be manipulated to derive new knowledge through reasoning using logic
/
  • Classroom quizzes

  • Demonstrate understanding of the concept of search space and various methods for conducting search for finding a solution
/
  • Classroom quizzes

  • Demonstrate understanding of how game playing systems can be created using search techniques in combination with heuristics
/
  • Classroom quizzes
  • Assignment

  • Describe a basic understanding of the techniques that are used in Machine Learning
/
  • Classroom quizzes
  • Assignment

Resources:

Required reading material

1 / / Textbook:
Artificial Intelligence Illuminated, Author: B. Coppin, Publisher: Jones and Bartlett, 2004
2 / Topic notes and lecture slides (Available online)

Supplementary reading material

1 / Artificial Intelligence: A Guide to Intelligent Systems, 2nd edition
Author: Michael Negnevitsky, Publisher: Addison Wesley, 2004
2 / Artificial Intelligence: A Systems Approach,
Author: M. Tim Jones, Publisher: Jones & Bartlett, 2009
2 / Other material cited in lectures, topic notes and the course Web site

Software required

  • e2GRuleEngine shell for developing rule-based expert systems

Free download at:

  • MathWorks MATLAB with artificial neural network and fuzzy logic tool boxes (available in lab CCT 450).

Course Online Interface

This course can be accessed online in CougarView at: https://colstate.view.usg.edu

Username: lastname_firstname

Password: Same as your Novel network and CougarNet password

Contents such as lecture notes and assignments will be progressively added to the course during the semester.

How this course will work

This course will consist offace-to-face meetings, readings, classroom discussions, assignments, quizzes and a project. On a weekly basis, you will be required to:

  1. Attend twice-weekly class meetings on Mondays and Wednesdays, 7:30 to 8:45 PM in CCT 408;
  2. Download the week’s lectures and any other relevant material made available online through CougarView;
  3. Read lectures to review the main points of the week's lesson;
  4. Get a more in depth understanding by completing the readings from the text and/or other material referred to in the lecture notes;
  5. Take part in classroom discussions;
  6. Download the current assignment and work on it to meet the given deadline for submission through CougarView;
  7. Participate in online quizzes using CougarView during class meetings;
  8. Work in a team of three to implement and present a project.

Communication

  1. E-mail is the preferred means of communication. Please use CougarView e-mail for all course related messages.
  2. Always include your original message (and any responses to it) in your messages. This is helpful for me as I receive many student messages during the semester and may need to be reminded of any previous communication with you related to your current message.

Assessment components

Assignments / 40% of course assessment
Classroom quizzes / 25% of course assessment
Team Project / 35% of course assessment

Grading scale

A (Excellent) / 90% - 100%
B (Good) / 80% - 89%
C (Average) / 70-79 %
D (Poor, passing) / 60-69 %
F (Failing) / below 60 %
The WF grade is assigned when a student withdraws from a course after the W grade deadline (see Important dates/holidays) or when an instructor drops a student for excessive absences.

CourseAssignments

The course assignments will cover theoretical and practical aspects of some of the AI topics taught in the course. They will require you to read the topic material, carry out online research and do hands-on work.

Assignments are due at 11:59 P.M. (one minute before midnight) of the due date. Once submitted by this deadline, you can resubmit your assignment with further work until it has been graded. Assignments missing the specified deadline will not be graded.

When you have completed an assignment consisting of more than one file, zip all files into a single file (name it using your name, course name and assignment number), then upload and submit this one file into CougarView using the Assignments link. To zip an application in Windows, simply right-click the folder containing the application, select "Send To," then select "Compressed (zipped) Folder."

Classroom Quizzes

There will be weeklyclosed bookquizzes held every Mondayduring class meetings to test your understanding of the material covered in the week’s classes. You will take this weekly quiz through CougarView during the class meeting. There will be a brief discussion period before this quiz to clarify any issues covered during the week. So, make a habit of taking notes and writing down any questions you want me to answer before taking the quiz.

The quizzes will be timed and answers with some feedback will be available during the class for discussion. Do not miss quizzes as no makeup quizzes will be given.

Course Project

You’ll be expected to work in a team of three members to implement a hybrid intelligent system that combines any two intelligent system methodologies selected from the following: Fuzzy rule-based inferencing, evolutionary computation, artificial neural networks. The project will involve a 5-minute presentation of the project proposal in week 10 of the semester, and a 20-minute presentation of the project with results at the end of the semester.

Tentative weekly schedule (subject to change)

WEEK # / TOPIC / READINGS/DUE ASSESSMENTS
Week 1: (1/13-1/19) / Topic 1: Introduction to AI and intelligent systems / Course syllabus, topic note, text book chapters 1 & 2, any relevant articles
Topic 2: Rule-based expert systems / Topic notes, text book chapter 9, any relevant articles
Week 2: (1/20-1/26) / 1/20 MLK day – no classes
Topic2: Rule-based expert systems (cont’d) / Assignment 1 (AI)– Jan. 23
Quiz 1
Week 3: (1/27-2/2) / Topic 2 Rule-based expert systems (cont’d) / Quiz 2
Week 4:
(2/3-2/9) / Topic 3: Fuzzy systems / Topic notes, text book chapter 18, any relevant articles
Quiz 3
Monday, Feb. 3 - Deadline to withdraw from course without penalty of a WF grade
Week 5: (2/10-2/16) / Topic 3: Fuzzy systems (cont’d) / Quiz4
Assignment 2 (Expert Sys.)– Feb. 11
Week 6: (2/17-2/23) / Topic 3: Fuzzy systems (cont’d)
Topic 4: Artificial neural networks / Topic notes, text book chapter 11, any relevant articles
Quiz 5
Week 7: (2/24-3/2) / Topic 4: Artificial neural networks (cont’d) / Quiz 6
Assignment 3 (Fuzzy IS)– Feb. 25
Spring Break (no classes) – March 3-7
Week 8: (3/10-3/16) / Topic 4: Artificial neural networks (cont’d) / Text book chapters13 & 14,topic notes, any relevant articles
Quiz 7
Week 9: (3/17-3/23) / Topic 5: Evolutionary computation / Quiz8
Assignment 4 (ANN) – Mar. 18
Week 10: (3/24-10/30) / Topic 5: Evolutionary computation (cont.) / Text book chapter 3, any relevant articles
Quiz 9
Project Proposal Presentation
Week 11: (3/31-4/6) / Topic 6: Search methodologies / Text book chapter 4, any relevant articles
Quiz 10
Week 12: (4/7-4/13) / Topic 7: Game playing / Text book chapter 6, any relevant articles
Quiz 11
Assignment 5 (EC)) – Apr. 8
Week 13: (4/14-4/20) / Topic 8: Machine Learning / Text book chapter 10, any relevant articles
Quiz12
Week 14: (4/21-4/27) / Topic 8: Machine Learning (cont.)
Topic 9: Natural language processing / Quiz 13
Week 15: (4/28-5/4) / Topic 9: Natural language processing (cont.) / Text book chapter 20, topic notes, any relevant articles
Assignment 6 (Search/ML) – Apr. 29
Quiz15
Last class day: 5/5 / Review of course topics.
May 7-10, 12 / Project Presentation during CSU scheduled exam day (exact date to be announced)

Instructor responsibilities

As an instructor of this course, I am responsible for:

  • posting lecture materials online each week in a timely manner;
  • introducing each week’s topic during class meetings;
  • Clarifying and explaining topic materialin the class;
  • providing timely feedback to you on your homework as appropriate
  • responding to your concerns via e-mail in a timely manner (within 24 hours usually,except during holidays or whentravelling);

Student responsibilities

As a student in this course, you are responsible for:

  • managing your time and maintaining the discipline required to meet course requirements;
  • covering all readings, online and offline, in a timely manner;
  • actively participating in classroom learning and submitting all homework adhering to course deadlines;
  • reading any e-mail sent by me and responding promptly when required;
  • logging in to CougarView regularly to study new developments (“I didn’t know” or “I didn’t look on website” is not an acceptable excuse for failing to meet the course requirements);
  • maintaining classroom etiquette, which includes not distracting others in the class.Receiving phone calls, texting or Web surfing is distracting for all those around you including your instructor.Cell phones must be turned off – not just put on vibrate, and computer use is only allowed for purposes directly related to classroom activities such as viewing lectures, taking notes or participating in quizzes.

If you fail to meet your responsibilities, you do so at your own risk. I will try to give you my best in this course, but I cannot do so without your interest and collaboration!

Attendance policy

Class attendance is the responsibility of the student, and it is your responsibility to independently cover any materials missed. Class attendance and participation may also be used in determining grades. It is your responsibility to sign a roll sheet for every class meeting. Students with more than six (6) absences will be dropped from the course and receive a WF grade unless valid reasons are given for these absences. Missing an exam or quiz is considered an absence. Missed classes caused by participation in documented University-sponsored events will not count as absences provided you notify me of such anticipated absences in advance and as soon as possible.

Academic dishonesty policy

Academic dishonesty includes, but is not limited to, activities such as cheating and plagiarism (http://academics.columbusstate.edu/catalogs/current/acaregs_undergrad.php#acadmisconduct). It is a basis for disciplinary action. Any work turned in for individual credit must be entirely the work of the student submitting the work. You may share ideas but submitting identical assignments (for example) will be considered cheating. You may discuss the material in the course and help one another with concepts; however, any work you hand in for a grade must be your own.

A simple way to avoid inadvertent plagiarism is to talk about the assignments, but not reading each other's work or writing solutions together. For your own protection, keep old versions of assignments to establish ownership until after the assignment has been graded and returned to you. If you have any questions about this, please contact me immediately. All work that is not your own must be properly cited. This includes any material found on the Internet. Collaboration is not permitted on assignments or quizzes in this course, unless explicitly specified by the instructor.

If you have any questions about what plagiarism is, check the following sites:

  • Plagiarism: What It is and How to Recognize and Avoid It
  • Avoiding Plagiarism - MASTERING THE ART OFSCHOLARSHIP

No cheating in any form will be tolerated. The penalty for the first occurrence of academic dishonesty is a grade of F in this course. Other penalties include suspension from the Computer Science program at CSU and/or dismissal from the program. All instances of cheating will be documented in writing in the university records. Students will be expected to discuss the academic misconduct with the faculty member and the chairperson of the department.

For exams (including any type of closed book tests or quizzes), access to any type of written material or discussion of any kind (except with me) is not allowed. Academic dishonesty could involve:

  • Having a tutor or friend complete a portion of your assignments.
  • Having a reviewer make extensive revisions to an assignment.
  • Copying work submitted by another student.
  • Using information from online information services without proper citation.

Getting help

Student assistants at the UITS Helpdesk can help you with basic computer-related problems such as logging on to the network, saving your work, etc.

There are several tutors in the School of Computer Science who may be able to help you with some course-related work. Their schedule is posted in the School of Computer Science Tutor lab in room CCT450. You can always contact me through e-mail, phone, or in person during my posted office hours or by appointment at a mutually convenient time.

CSU's ADA compliance statement

If you have a documented disability, as described by the Rehabilitation Act of 1973 (P.L. 933-112 Section 504) and the Americans with Disabilities Act (ADA) and subsequent amendments and would like to request academic and/or physical accommodations, please contact the Office of Disability Services in the Schuster Student Success Center (room 221), 706-507-8755, as soon as possible. Course requirements will not be waived, but reasonable accommodations may be provided as appropriate.

Student Portfolio

Students are encouraged to keep and maintain a portfolio of all of their work (assignments, projects, etc.) throughout their academic program. It is recommended that you keep a copy on your personal H: drive atCSUand back it up regularly on your own portable media.

Important dates/holidays

First day of classes: Monday, January 13

Schedule change

Drop/Add Courses: January 13-17

Martin Luther King Holiday (no classes, offices closed): Monday, January 20

Deadline to Withdraw from course: Friday, February 4

Spring break (no classes): March 3-7

Last class day for all courses: Monday, May 5

Project presentation: May 7-1012 (exact date to be announced).

(Note, there are no exams for this course)

1 of 8

Artificial Intelligence