Syllabus

Pattern Recognition (Spring 2020)

Syllabus

Update: Late Spring 2020

RIT has asked instructors to update students on changes to course syllabi, now that all courses have moved online. This syllabus remains unchanged. With minor changes to the schedule, the instructor anticipates that the course can be completed as planned, without undue challenges for students.

Course Description

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. using HMMs and SCFGs). Students will present current research papers and complete programming projects such as optical character recognizers.

Pre-requisites: CSCI-331, CSCI-630 or permission of instructor. Credit Hours: 3

Course Outcomes

Assessment method(s) for each learning outcome are shown in italics.

Students will understand Bayesian Decision Theory, the canonical classifier model, and how different classification methods define decision boundaries. Evaluation: Assignments, and projects.
Students will be able to apply performance evaluation methods for pattern recognition. Evaluation: Projects.
Students will be able to select appropriate techniques for addressing recognition problems. Evaluation: Assignments, and projects.
Students will be able to implement basic pattern recognition algorithms. Evaluation: Assignments and projects.
Students will be able to summarize current pattern recognition research verbally and in writing. Evaluation: Assignments and research paper presentations.

Instructor Contact

Dr. Richard Zanibbi

Office: GOL-3551

E-mail: rxzvcs@rit.edu

Website: http://www.cs.rit.edu/~rlaz

Phone: 585-475-3551

Note: I try to respond to email within 24 hours. However, email received on Friday afternoons and weekends I may not respond to until the following Monday. I will also not answer homework or project-related questions the day they are due.

Course Policies

Submissions. All homework, both written and code, must be handed in via MyCourses. Note that for all programming homeworks/labs, they must be (easily) executable on the CS lab Linux machines. More details on allowed and available libraries etc will be given with each assignment (what is allowed for some may not be allowed for others).
Late Policy. Late submissions will be accepted up to 48 hours after the deadline, with a 20% penalty.
Grades must be disputed within one week after graded work is handed back. After this, grades will not be updated.
Homework and Projects. The homework assignments (not projects) in this course are to be done on your own. You may discuss homeworks with your classmates and the instructor, but you must create all submitted work for assignments on your own. It is not acceptable for a student to prepare an answer or answer set and share this with other students. Projects will be done by student groups - for this work, the same restrictions apply as for homeworks, except to the group rather than the individual.
Lecture. This is an advanced course that will cover a wide variety of topics, some being complex and/or counter-intuitive. Students should raise their hands to ask a question when things are unclear, they want to check their understanding, or have an idea to share. Sometimes the instructor will not call on the student right away to make sure that the course progresses at a reasonable pace. Students are always welcome to send questions over email or talk to the instructor during office hours.
Readings/Research Paper Presentations. Students are expected to actually complete all assigned readings. For research papers, students will be giving presentations in small groups. The instructor will provide sources for papers one week before a presentation is given. Paper presentations will be given by groups of two or three 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. Presentations will be graded based on their technical content and clarity.
Exam. For our 'exam,' all project teams will present their finished projects. Each presentation will run about 10 minutes, with a short break half-way through, and a class discussion at the end.
Grading. For full points, deliverables in the course including question answers, code, presentations and write-ups must be:

Correct and complete (all parts/aspects of the question are covered).

Jusitified: if an assignment or test question asks for an explanation or justification, it must be provided for full points.

Clearly written: answers/reports should be written with care and attention to language, and provide the context needed to understand the answer with a reasonable effort. Note that the goal here is clarity, not complexity. Make your answer understood in simple terms wherever possible.

Provided in the requested format. For example, files are submitted in the correct format, a question that asks for a written description is not a bulleted list, etc.

Attendance Policy and Absences from Class

This section was added at the request of Dr. Ellen Granberg, Provost and Senior Vice President for Academic Affairs.

RIT’s official policy on attendance states that:

"Absences, for whatever reason, do not relieve students of their responsibility for fulfilling normal requirements in any course. In particular, it is the student’s responsibility to make individual arrangements in advance of missing class due to personal obligations such as religious holidays, job interviews, athletic contests, etc., in order that he or she may meet his or her obligations without penalty for missing class." (RIT Governance Policy D4.0, Section I.B)

Therefore, if a student needs to miss class, there are mutual responsibilities for students and faculty. It is the student’s responsibility to notify the faculty member in advance of the planned absence. With advance notice of the planned absence, it is the faculty member’s responsibility to ensure that the student can fulfill all class assignments and expectations without penalty or bias.

To encourage student communication about planned absences, this expectation should be stated in the first class and included in the syllabus posted in MyCourses.

Required Materials

All required materials for the course will be provided through MyCourses. Some additional resources may be found on the resources web page.

Grading

Component	Weight
4 3 Assignments	30%
3 2 Research Paper Summaries/Presentations	15%
3 Projects (Classification, Segmentation, Parsing)	45%
Final Project Presentation (Exam)	10%

Common Course Policies for the RIT Department of Computer Science

Rescheduling an Exam. Exams can not be made up except for real emergencies in which case proper documentation (like a doctor's note) will be required. If at all possible, you should contact me prior to the exam. Oversleeping, cars that don't start etc. do not constitute a valid excuse. RIT's Academic Senate revised the Final Examination Policies on March 28, 2013. Please refer to the policies for related questions.
Course withdrawal. During the add/drop period, you may drop this course and it will disappear from your transcript. After that time, you can only withdraw from the course; the course will appear on your transcript with a grade of W. See the institute's calendar regarding the add/drop period and latest withdrawal date.
Disability Services. RIT is committed to providing reasonable accommodations to students with disabilities. If you would like to request accommodations such as special seating or testing modifications due to a disability, please contact the Disability Services Office. It is located in the Student Alumni Union, Room 1150; the web site is www.rit.edu/dso. After you receive accommodation approval, it is imperative that you see me during office hours so that we can work out whatever arrangement is necessary.
Academic Integrity. The Department of Computer Science Policy on Academic Honesty will be enforced. You should only submit work that is completely your own. Failure to do so counts as academic dishonesty and so does being the source of such work. Submitting work that is in large part not completely your own work is a flagrant violation of basic ethical behavior and will be punished according to department policy.

Home/News

Schedule

Syllabus

MyCourses

Resources