ECGR6119/8119 - Applied Artificial Intelligence (3)

Catalog Data The theory of machine intelligence. Computational methods for modeling machine intelligence including machine vision and automatic decision making from sensor measurements. Applications of this theory to autonomous robotic decision making such as navigation and industrial quality control.
Lecture Times Tuesday, Thursday 9:30-10:45
Lecture Room EPIC G222
Reference Pattern Recognition and Machine Learning, Christopher Bishop, Springer, 2007.
Additional References Pattern Classification, Duda, Hart & Stork, John Wiley & Sons, 2001.
Goals The objective of this course is to provide students with a working knowledge required to analyze and design computer vision and pattern recognition algorithms and systems.
Prerequisite Permission of the Department
Class Topics

Probability Theory
Bayesian estimation
Multidimensional Gaussian Distribution
Basic of information theory
Linear regression models
Linear models for classification
Advanced Topics such as : face recognition, manifold learning, markov random field

Outcomes The following competencies should be imparted to the students:
1. An understanding of basic probability theory as applied in pattern recognition contexts (assessment by homework).
2. The ability to implement basic pattern recognition algorithms (assessment by projects and homework).
3. The ability to implement basic classification algorithms (assessment by projects and homework).
4. Hands-on experience with various computer tools for implementing and testing pattern recognition systems in a variety of projects (assessment by design project).
Computer Usage Students design, simulate, and analyze a variety of computer vision and pattern recognition projects. MATLAB should be accessible as a tool for completing projects.
Laboratory Students use computer laboratories for the implementation of the design projects outside of class.
Design Content The design projects for the course vary from semester to semester.
Grading *

There no two exams in this course. Grades are determined by performance on homeworks, projects, and in-class presentations. The weight of each item in determining the final grade is as follows:
Homework 10%
Quizzes 10%
Mid-Term 20%
Final 30%
Projects & Presentations 30%

Follow-up Courses N/A
Academic Integrity Students have the responsibility to know and observe the requirements of the UNCC Code of Student Academic Integrity (2001-2003 UNCC Catalog, p. 275) . This code forbids cheating, fabrication or falsification of information, multiple submission of academic work, plagiarism, abuse of academic materials, and complicity in academic dishonesty.
Notes Semester syllabus will be provided to the students on the first day of class.
Coordinator A. Willis, Professor of Electrical & Computer Engineering
Prepared by A. Willis, August 16, 2012

* Grading policy may be modified by the instructor for each section of the course.

* Grading scale : 90-100 A, 80-89 B, 70-79 C, with ``curve,'' if any, entirely at the discretion of the instructor. Quizzes may be given without warning.

Important Notes for Students

Students in this course seeking accommodations to disabilities must first consult with the Office of Disability Services and follow the instructions of that office for obtaining accommodations.

The use of cell phones, beepers, or other communication devices is disruptive, and is therefore prohibited during class. Except in emergencies, those using such devices must leave the classroom for the remainder of the class period.

Students are permitted to use computers during class for note-taking and other class-related work only. Those using computers during class for work not related to that class must leave the classroom for the remainder of the class period.

Collaboration (not copying) on homework and computer projects is encouraged. However, students may NOT share program code or report material. You must read the textbook; it is impossible to cover all material during class.