CEG-726 Pattern Recognition

Spring 2008

 

 

CRN: 39057                        Lecture: 2:15 – 3:30,Tu, Th,                      Location: 066 UH
Instructor: A. Goshtasby          Office Location: 495 Joshi            Phone: 937-775-5170
Email: agoshtas@wright.edu   Office Hours: 1:00 – 2:00 PM, M, T, W, T or by appoint.

No. Units: 4

Prerequisites: A course in probability theory and knowledge of programming

Textbook:

Pattern Recognition, 3rd Edition
S. Theodoridis and K. Koutroumbas
Academic Press 2006

Supplemental Reading

To be provided. Each student will read a paper on an application of pattern recognition and will make a presentation to class.

Contents:

  1. Introduction and Preliminaries
  2. Clustering Basics
  3. Hierarchical Clustering Algorithms
  4. Sequential Clustering Algorithms
  5. Bayesian Decision Theory
  6. Feature Selection
  7. Feature Generation
  8. Template Matching
  9. Pattern Recognition Applications

 

Purpose of Course:

This course will cover fundamentals of Pattern Recognition, including supervised learning and clustering.

Learning Goals:

Students will learn theory as well as practice in this course. Some of the materials learnt in class will be practiced through computer implementation.

Projects and Exams:

There will be two programming assignments and two midterm exams. In addition, each student will read a paper on an application of pattern recognition and present to class.

Grading Policy:

Programming assignments will worth 40%, midterm exams will worth 40%, and presentation will worth 20% of the overall grade. Grades will be assigned as follows. A: [91..100], B: [81..90], C: [71..80], D: [61..70], F: [0..60].

Calendar:

Assignment 1

Handed out:     4/10/08            Due: 4/24/08

Assignment 2

Handed out:     4/24/08            Due: 5/8/08

Midterm Exam 1

On 4/29/08

Midterm Exam  2

On 5/29/08

Reading Assignments

Handed out: 5/15/08