86-375/675 Computational Perception

Carnegie Mellon University

Spring 2012

Course Description

The perceptual capabilities of even the simplest biological organisms are far beyond what we can achieve with machines. Whether you look at sensitivity, robustness, or sheer perceptual power, perception in biology just works, and works in complex, ever changing environments, and can pick up the most subtle sensory patterns. Is it the neural hardware? Does biology solve fundamentally different problems? What can we learn from biological systems and human perception? In this course, we will first study the biological and psychological data of biological perceptual systems in depth, and then apply computational thinking to investigate the principles and mechanisms underlying natural perception. The course will focus on visual perception this year. You will learn how to reason scientifically and computationally about problems and issues in perception, how to extract the essential computational properties of those abstract ideas, and finally how to convert these into explicit mathematical models and computational algorithms. The course is targeted to neuroscience and psychology students who are interested in learning computational thinking, and computer science and engineering students who are interested in learning more about the neural basis of perception. Prerequisites: First year college calculus, some linear algebra, probability theory and programming experience are desirable.

Course Information

Instructors	Office (Office hours)	Email (Phone)
Tai Sing Lee (Professor)	Mellon Inst. Rm 115	tai@cnbc.cmu.edu (412-268-1060)

Class location and time: Mellon Institute Rm 130 Monday/Wednesday 1:30 p.m - 3:00 p.m.
Website: http://www.cnbc.cmu.edu/~tai/cp12.html (course info)
Blackboard: http://www.cmu.edu/blackboard/ (Both 375/675 students should use 375 BB for access of course materials and announcements. 675 students should also check their 675 BB for additional requirements and works

Classroom Etiquette

Please turn OFF your laptop, cell phones or any other electronic devices in the classroom.

Grading Scheme

Evaluation	% of Grade
Assignments	50
Quiz 1	10
Quiz 2	10
Final Exam	30
Term project (optional)	17
675 Term Project	Required

Grading scheme: A: > 85, B: > 75. C: > 65.

Assignments

(A) 12 weekly assignments (5 points each), each with three parts: (1) Each student is responsible reading the textbook or doing research to answer questions posed by the professor. (2) Each student is also responsible for coming with a question that interests him/her the most on the topic, and for providing his/her answer for that question. (3) Participation in class discussion of these questions.
(B) The assignment answer should be in pdf file, and cannot exceed one page per part, and should be submitted before class to blackboard.
(C) Collaboration in team of two is allowed on (A1). Each person should work on (A2) alone. But each pair can only work together at most three times during the semester.
(D) Only the top 10 scores will be counted, with a max total of 50.
(E) Excess homework grades (over 50) can count toward the final exam.

Term Project

Term project is optional for 375 students. A student can use the OPTIONAL term project (with a max score of 17 points) to replace the combined grade of 20 points worth of assignment/quiz grades, or contribute to the final exam grade. No collaboration is allowed. It will require a 6 pages written final report and a presentation to the class. Matlab codes and additional output should also be submitted as supplementary materials in a different pdf/doc file and/or matlab zip files.
Term project is required of 675 students, and will be graded in percentile according to written report and presentation. Respectable performance in term project (e.g. achieving a top 65 percentile among all class projects) in addition to achieving 85 percent in the other scores, is required for an A. Students are encouraged to work on issues that are not covered in the course, for example, adaptation and visual learning, art and perception, neural basis, etc.

Examinations

There will be two quizzes to test understanding of the materials covered in the book and issues discussed in the lectures. The closed-book Final Exam will ask pre-distributed questions. Students are encouraged to study together for these exams.

Late Policy

No late homework will be accepted. Blackboard submission after the starting of class time is considered late.
No extension possible for the term paper.

Syllabus

Date	Lecture Topic	Relevant Readings	Assignments
	SENSORY CODING
M 1/15	0. No Class (MLK celebration)	ch. 1
W 1/17	1. Overview	ch. 1
M 1/23	2. Auditory senses	Chase
W 1/25	3. Visual senses	ch 6
M 1/30	4. Retina processing	ch 3
W 2/1	5. Efficient coding	handout
M 2/6	6. Linear Transforms	handout
W 2/8	7. Frequency perception	ch 9
	EARLY PERCEPTUAL INFERENCE
M 2/13	8. Bayesian inference	ch 13
W 2/15	9. Edges and contours	ch 5
M 2/20	10. Figure from ground	ch 7
W 2/22	11. Perceptual organization	ch 7
M 2/27	12. Motion perception	ch 14
W 2/29	13. Motion computaton	ch 15
M 3/5	14. Review/Discussion
W 3/7	15. Quiz 1
F 3/9	Midterm Grade due 6 p.m.
M 3/12	Spring break
W 3/14	Spring break
	SURFACE PERCEPTION
M 3/19	16. Brightness perception	ch 16
W 3/21	17. Surface representation	ch 2
M 3/26	18. Binocular Stereo	ch 18
W 3/28	19. Binocular Stereo	ch 19
M 4/2	20. Texture perception	ch 2
W 4/4	21. Cue combination	ch 20
	OBJECT AND SCENES
M 4/9	22. Color Invariance	ch 17
W 4/11	23. Hiearchy and Deformation	ch 10
M 4/16	24. Object perception	ch 8
W 4/18	25. Context and scenes
M 4/23	25. Attention and Binding	ch 4
W 4/25	26. Student Presentation
M 4/30	27. Student Presentation		Term paper due.
W 5/2	Quiz 2
X 5/X	FINAL EXAM

Questions or comments: contact Tai Sing Lee
Last modified: Jan 9, 2012, Tai Sing Lee