CS688
Pattern Recognition (Fall 2012)

Meeting Time and Location:
W 4:30 pm - 7:10 pm, Robinson Hall B208

Instructor: Prof. Daniel Barbará.
Email: dbarbara (at) gmu (dot) edu
Office: Eng. Bldg 4420
Office hour: by appointment

Graduate TA: TBA

Course Home Page
CS688

Overview
This course provides an introduction to the fundamental concepts in pattern recognition. Topics include:

• Supervised Learning, Linear Models, Statistical Decision Theory
• Linear Methods for Regression
• Linear Methods for Classification
• Kernel Methods
• Model selection and assesment (other topics as time permits)

  Textbook

  • The Elements of Statistical Learning By Hastie, Tibshirani and Friedman
  • A first course in Machine Learning by Rogers and Girolami

  Grading Policies
  There will be written homeworks, programming assignments, a final project a in-class midterm exam, and a final exam. Both the final and midterm are open-book and open-notes. The final exam will be comprehensive, i.e., it will cover the entire course. Missed exams must be arranged with the instructor BEFORE the exam.  Documentation of the illness (doctor's note) is required.  No early exams will be given and make-up exams are strongly discouraged.

  End-of-semester numeric scores will be weighted as follows (tentative plan):
  • 35% Assignments
  • 35% Exams
  • 30% project In order to obtain an A, your final score should be at least 90. A total score of 49 or less will result in an F.

    Late Policy

    Late homework will be accepted with a penalty of 20% per day within 3 days after deadlines and will not be accepted three days after due, unless under prearranged conditions.

    Honor Code
    You are expected to abide by the honor code.  All assignments and exams are individual efforts. Please refer to GMU Academic Policies and Computer Science Department Honor Code.  Any violation of the honor code will result in a zero of the assignment/exam, and may result in an F for the class.

    School Calendar

    Disability