Artificial Intelligence
CSC 415/515

Fall 2013

Section 001: T-R, 3:30-4:45 PM, CIS1006

Course Schedule

Prerequisite

CSC 332

Description

CSC 415/515 is an introduction to key concepts and applications of artificial intelligence. While conventional artificial intelligence focuses upon knowledge representation and expert systems, this course will center upon finding solutions for search, optimization, and constraint satisfaction problems such as may commonly arise in application areas as signal and object detection, pattern recognition, and classification, scheduling, system control, and reasoning under uncertainty. A variety of techniques will be studied including both conventional search and optimization methods as well as biologically inspired computing using neural networks, genetic algorithms, particle swarms, or fuzzy logic. The course meets for three lecture hours per week. Additional meetings may be required for group work, laboratory exercise demonstrations, or programming projects.

 

A central goal of this course is to provide the student with practical experience with the algorithms and techniques for deriving human-like behavior from machines.  Accordingly, students will be required to participate in programming projects that entail the design, development, implementation, and testing of software to solve a wide variety of problems. These may include route planning, sensor signal processing, image processing, or control. Students will be expected independently to:

  1. Develop programs to implement various techniques;
  2. Conduct experiments to assess the relative merits of alternative techniques for problem solving;
  3. Document their findings through written reports; and
  4. Present their findings to their peers.

Required Text

M. Tim Jones, Artificial Intelligence: A Systems Approach, Infinity Science Press, Hingham, MA 02043.  ISBN 978-0-9778582-3-1

Instructor

Contact information

Professor Gene A. Tagliarini

CIS 2038

tagliarinig@uncw.edu

(910) 962-7572

Office hours

M-W-F, 9:00-11:00 AM and M,W 2:00-4:00 PM

Other office hours may be arranged by appointment.

Open Laboratory

CIS 2006 (TBD. Previously,  Sun 7-10pm; Mon 7-10pm; Tue 7-10pm; Wed 9-11pm; Thu 7-10pm)

Other office hours may be arranged by appointment.

Student Learning Outcomes

 

The Student Learning Outcomes (SLOs) for CSC 415 are:

  1. Students develop knowledge of representational issues and their relationship to applications of artificial intelligence.
  2. Students learn and implement search methods, including depth-first, breadth-first, and heuristic search techniques, to find solutions for computationally intractable problems.
  3. Students learn to model natural processes that perform computation.
  4. Students implement computational paradigms that mimic natural processes.
  5. Students develop knowledge of algorithm and implementation alternatives that enables them to choose appropriately.
  6. Students develop skills in writing technical reports that describe findings that arise from application of software that they develop.

 

In addition, CSC 515 possesses the following SLOs

  1. Students demonstrate professional writing skill by preparing a paper for submission to a technical conference.
  2. Students demonstrate independent learning and technical presentation skill by investigating an AI technique that is not covered in CSC 415/515, developing and delivering a an instructional presentation describing the techniques and demonstrating its application to a problem of interest.

 

Mapping of SLOs to Course Artifacts

 

 

Mapping of SLOs to Course Artifacts

Assessment Instruments

SLO

Markov Model

Feedforward neural network

Nearest Neighbor Classifier or k-means clustering

Bayesian Classifier

Genetic Algorithms

Particle Swarm

Mid-term Test

Final Exam

Course Research Project

Topic Investigation and Presentation

1

X

X

X

X

X

X

X

X

X

 

2

 

 

 

X

X

 

 

X

 

3

X

X

X

X

X

X

X

X

X

 

4

X

X

X

X

X

X

 

X

 

5

X

X

X

X

X

X

X

X

X

 

6

X

X

X

X

X

X

X

 

7

 

 

 

 

 

 

 

 

X

 

8

 

 

 

 

 

 

 

 

 

X

 

Grading

Weighting

·       Tests will be weighted 40% (2 tests* 20% each = 40% total),

·       Programming projects will be weighted a total 36% of the final grade, and

·       The report and presentation of findings 34%.

Note: the programming assignments are essential to preparing the final report; hence, their cumulative effects influence 70% (36% programs + 34% final report) of the final grade.

 

Undergraduates, your final grade will be determined based upon your conduct and report of personally conducted research as well as your performance on the mid-term, final examinations, and programming projects. Please note that a major component of your final grade is based upon your research, a written report of the findings of experimental processes, and a presentation of your findings to your peers.  It is important that you identify a research problem of interest early, establish a baseline for performance comparisons, independently and personally develop implementations of algorithms, and use your own implementations of algorithms to evaluate actual performance on your problem of interest.

 

Graduate students are required to:

1.     Implement and demonstrate all six AI computational paradigms described in the syllabus above (Markov model, a feedforward neural network, a nearest neighbor classifier or k-means clusterer, a Bayesian classifier, a genetic algorithm, and a particle swarm). This accounts for 30 of the 36% for programming projects.

2.     Investigate and present to the class an AI technique not already on the schedule. Since the presentation will require a demonstration of an implementation, this will account for 6 for the 36% for programming projects;

3.     Apply at least four AI paradigms to a research problem of interest and to report the performance of these algorithms with reference to a conventional approach for the same research problem;

4.     Prepare their written report of findings in a manner suitable for submission to a conference in consideration for publication;

5.     Investigate, present and demonstrate an AI technique not covered during the instructor’s lectures.

 

Test schedule

The tests will be given according to the following schedule:

            Test                                         Date

            Mid-term                                Thursday, 3 October

Final Exam                             Tuesday, 10 December, 3:00 – 6:00 PM

Grade scale

Your final grade will be determined according to the following scale:

            Final average              Grade 

            90-100                         A

            80-89.999                    B

            70-79.999                    C

            60-69.999                    D

            less than 60                 F

In addition to an exceptional performance on the intermediate tests and final exam, a final grade of "A" will require that the student's programming projects correctly provide all specified functionality, and that his/her final report and presentation constitute an exemplary description of the student’s experimental findings.

 

The instructor reserves the right, solely at his own discretion, to curve grades.

Incomplete grades

Incomplete grades are given only very rarely and only when the student is

  1. Otherwise passing the course,
  2. Able to complete the work of the course entirely on his/her own, and
  3. Prevented from completing the course by verified unforeseen circumstances beyond the control of the student. 

The instructor MUST be able to certify all three of these factors to the chair before assigning a grade of "I". 

Key dates

Event                                                                           Date

Last day to withdraw with W (undergraduate)          Monday, 14 October

Last day to withdraw with W (graduate)                   Monday, 14 November

 

Understanding the Schedule

A tentative schedule is available online. At the discretion of the instructor, the reading schedule may be adapted to include additional selections. You should explore the content of the text, the Web, and the library as needed to supplement class discussions. Please express leadership by taking the initiative to read about areas if interest without waiting for specific reading assignments to cover a topic that attracts your attention. There will not be time in class to discuss all of the required reading, so you should plan significant time for independent study. In addition, you should allocate time for office hours visits as appropriate. If you have questions regarding topics in the text, please e-mail your questions to the instructor, ask during class, visit during office hours or make alternative meeting arrangements.

 

Demonstrations or laboratory documentation of functioning programs are due on the dates shown in the schedule.  Late penalties of 25%, 50%, and 100% apply for assignments delivered up to 24 hours late, more than 24 but less than 48 hours late, and more than 48 hours late, respectively.

Attendance Policy

Regular attendance and vigorous participation in class are expected but not required.  However, if you desire the "benefit of the doubt" in any matter related to your grade in the class, you will routinely be present, ask relevant questions, and cooperate with the instructor as well as the course objectives.  Each student is personally responsible for material covered during each class meeting.

Americans with Disabilities Act

If you have a disability and need reasonable accommodation in this course, you should inform the instructor of this fact in writing within the first week of class or as soon as possible.  If you have not already done so, you must register with the Office of Disability Services in Westside Hall (ext. 3746) and obtain a copy of your Accommodation Letter.  You should then meet with your instructor to make mutually agreeable arrangements based on the recommendations of the Accommodation Letter.