Instructor
Pedro Felzenszwalb
Email: pff (at) brown.edu
Office: Barus & Holley 355
TA
Jeova Farias (jeova_farias_sales_rocha_neto@brown.edu)
Office hours:
1-3pm Monday ERC 250
3-5pm Thursday in ERC 250
(To access ERC 250 you need your Brown ID)
Course description
This course covers fundamental topics in pattern recognition and machine learning. We will consider applications in computer vision, signal processing, and information retrieval. Topics include: decision theory, parametric and non-parametric learning, dimensionality reduction, exact and approximate inference, generalization bounds, support vector machines and neural networks.
Prerequisites: probability and statistics, linear algebra, calculus and programming experience.
Textbook
C. Bishop, Pattern Recognition and Machine Learning, Springer
Grading
Grading will be based on regular homework assignments and two
exams. Homework will involve both mathematical exercises and
programming assignments in Matlab.
Students may discuss and work on homework problems in groups. However, each student must write down the solutions independently. Each student should write on the problem set the set of people with whom s/he collaborated.
The breakdown of the final grades will be approximatelly as follows:
Homeworks 50%
Midterm 20%
Final 30%
Important dates:
Midterm: TBA in class.
Final exam: December 14, 2pm
Previous Course
Spring 2017