RIT Department of Computer Science
4005-738-01 Pattern Recognition, Fall 2012
Lectures: 2:00 - 3:50pm Mondays and Wednesdays, GOL-3550 (Mon), GOL-3560 (Wed)
Instructor: Richard Zanibbi
Office hours: 2:00-3:50pm Tuesdays and Thursdays, GOL-3550 (Lab on 3rd floor)
An introduction to pattern classification and structural pattern recognition. Topics include: Bayesian decision theory, evaluation, clustering, feature selection, classification methods (including linear classifiers, nearest-neighbor rules, support vector machines, and neural networks), classifier combination, and recognizing structures (e.g. HMMs and Stochastic Context-Free Grammars). Students will present current research papers, as well as implement recognition systems such as Optical Character Recognizers. Class hours: 4, Credits: 4
Prerequisites: 4003-455 (Artificial Intelligence) or 4005-750 (Introduction to Artificial Intelligence), or Permission of the instructor.
At the end of this course, students will be able to:
I will be holding office hours (GOL-3551) Tuesdays and Thursdays from 2-3:50pm. If you are unable to make those times and need to speak with me outside of class, please send me email to set up an appointment. I try to respond within 24 hours to emails that I receive. Note however, that I may not answer emails about course projects and assignments that are received 24 hours or less before the assignment or project is due.
We will be working from multiple sources this quarter, and readings will be posted on the MyCourses page for the course. Additional sources on pattern recognition are provided in the Resources section of the course web page.
Programming for the course will be done in Python, using the following libraries:
There is a significant amount of mathematical content in the course. If you find that you are challenged by notation or mathematical concepts used in the course, please make use of the instructor's office hours, or email the instructor to set up an appointment. If you need additional help after consulting the instructor, you are encouraged to make use of the RIT Academic Support Center, which has a drop-in center and a number of other useful resources.
| 30% | Assignments (3) |
| 40% | Projects (2: 20%, 20%) |
| 30% | Research Paper Presentations (3) |
Assignments will be given out one week before they are due. They will include some combination of written questions and small programs/experiments. There will be two course projects, in which we will incrementally construct a complete end-to-end system for recognizing mathematical expressions:
Projects will be assigned two weeks before they are due. All assignments and programming projects will be completed individually.
A central part of the course is the presentation and discussion of research papers. The instructor will provide sources for papers one week before a presentation is given. Papers will be presented on classification (week 4), segmentation/clustering (week 7) and parsing (week 10). Presentations will be given by groups of two students. The instructor will try to provide time for discussion of the papers presented in-class. Presentations will be short, between 5 and 10 minutes, depending upon the number of students presenting. Presentations will be graded based on their technical content and clarity.
If you have special needs for seating, tests, note-taking services or other matters due to a disability, please contact the Disability Services Office (www.rit.edu/dso). If you receive approval for accomodation within the course, please contact me as soon as possible so that we can make the necessary arrangements.
Late submissions may be submitted at most two days late, with a 10% grade penalty each day. After 48 hours, late submissions will not be accepted. Note that the MyCourses dropbox for assignments will close 48 hours after the due date (i.e. 48 hours after the deadline).
Exams will only be rescheduled in the case of difficult situations for which there is formal documentation (e.g. a doctor's note). Contact the instructor as soon as possible if you encounter scheduling or other issues regarding the exams.
RIT policy allows you to withdraw from a course with a grad of W on or before the Friday of the 8th week in the quarter. After this date, your instructor cannot give you a W, but must assign you a grade based on your work.
This course has been designed so that you can complete all the work in one quarter. Thus incomplete grades will be given only in the most exceptional circumstances, and then only by prior arrangement with the instructor. Your instructor has the final say in this matter.
Students may discuss assignments and projects with others, but submitted work (papers and code) must be created independently by each student or group, and not copied from another student or other source.
All borrowed ideas, text, or code used in papers and assignments must be cited appropriately. Citations must be provided using an accepted format for academic journals in computer science (e.g. ACM or IEEE styles). Providing only a URL for a references is unacceptable: in the case where a URL is appropriate (e.g. for software), the author, title, and date for the document associated with the link must be provided with the citation. In cases where it appears that copying of material or plagiarism has occurred, the Department of Computer Science Policy on Academic Integrity will be followed.