15-386/686 Neural Computation

Carnegie Mellon University

Spring 2012

Course Description

Neural Computation is an area of interdisciplinary study that seeks to understand how the brain computes to achieve natural intelligence. It seeks to understand the computational principles and mechanisms of intelligent behaviors and mental abilities -- such as perception, language, motor control, and learning -- by building artificial systems and computational models with the same capabilities. This course explores how neurons encode and process information, adapt and learn, communicate and compute at the individual level as well as at the levels of networks and systems. It will cover basic concepts in computational and neuronal modeling, information theory and coding, neural networks and learning, neural data analysis and decoding, signal processing and system analysis, statistical learning and probabilistic inference. Concrete examples will be drawn from the visual system and the motor system, including brain computer interface and neural decoding. Students will learn to perform quantitative analysis and perform computational experiments using Matlab. No prior background in biology is assumed. Prerequisites: 15-100, 21-120 or permission of instructor. 21-241 preferred but not required.

Course Information

Instructors	Office (Office hours)	Email (Phone)
Tai Sing Lee (Professor)	GHC 8017 (Tuesday 1:45-2:45 p.m.) also after each class	tai@cnbc.cmu.edu (412-268-1060)
Andrew Noh (TA)	HH 1st floor study rooms near the 1300 corridor (MW 3-4:30)	anoh@andrew.cmu.edu

Class location and time: Wean 5415 Tuesday/Thursday 3:00 p.m - 4:30 p.m.
Website: http://www.cnbc.cmu.edu/~tai/nc-12.html (course info)
Blackboard: http://www.cmu.edu/blackboard/ (Both 386/686 students should use 386 BB for access of course materials and announcements. 686 students should also check their 686 BB for additional readings

Classroom Etiquette

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
686 Term Project	Required

Grading scheme: A: > 88 B: > 75. C: > 65.

Assignments

4 or 5 programming and mathematical assignments. The solution should be in pdf file, and should be submitted before class to blackboard.
Collaboration in team of two is allowed for the first two assignments.

Term Project

Term project is optional for 386 students. A 386 student can use the OPTIONAL term project to replace quiz/assignment grades, and/or to contribute to the final exam grade. The maximum grade for the term project is 17 points. That is, it worths up to 85 percent of the 20 points in the assignments/quiz/final grades. Collaboration is allowed, but in this case, the maximum grade worths up to 75 percent of 20 points, i.e. 15 points each person. 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 686 students, and will be graded in percentile according to written report and presentation. Collaboration is allowed. Top 65 percent term project performance (relative to all (386/686) students' term projects) (in addition to achieving 88 percent in the other scores) is required for an A. Students are encouraged to work on issues that are not covered in the course.

Examinations

The quizzes and final exam will cover materials covered in lectures. Students are encouraged to study together for these exams.

Late Policy

You will have about 2 weeks to do each homework assignment. Homework report should be type-written. You should submit a hardcopy, documenting all the answers and results in class on the due day, as well as a softcopy of write-up and the codes to Blackboard before noon on the due day. Blackboard submission after noon is considered late.
All students are allowed to collaborate in the FIRST two assignments ONLY to facilitate matlab learning. Each should submit a copy of the solution, but should list his/her partner, if any, on the first page of the report.
Each student has ONE chance to turn in one of five homework assignments late within one week without penalty. However, Blackboard submission after noon on the due day is considered late.
If you need to submit a late homework after using the one free late, you will receive 5 percent deduction from maximum credit per lecture the solution set is released.
No extension possible for the term project.

Final Grade Assignment

386 students: A for total grade >= 88 %, B: < 88 AND >= 75, C: < 75, >=60. F for cheating.
686 students: A for total grade >= 88 % and top 65 term project performance.

Syllabus

Date	Lecture Topic	Relevant Readings	Assignments
	LEARNING AND REPRSENTATION
T 1/17	1. Introduction	ch 1
R 1/19	2. Neurons and spikes
T 1/24	3. Sounds to spikes
R 1/26	4. Cochlear coding
T 1/31	5. Synapses and transmission		HW 1 out
W 2/1			Matlab tutorial /Help : 5:30-7:00
R 2/2	6. Precion and Stochasticity
T 2/7	7. Hebbian learning		Help session
R 2/9	8. Neural Tuning		HW 1 due. HW 2 out;
T 2/14	9. Linear Transforms
R 2/16	10. Redundancy reduction
T 2/21	11 Visual Representation
R 2/23	12. Sparse coding		HW 2 due. HW 3 out
T 2/28	13. Competitive Learning
R 3/1	14. Computational map
T 3/6	Quiz 1
R 3/8	15. Assocative Learning		Project Proposals
F 3/9	Midterm Grade due 6 p.m.
T 3/13	Spring break
R 3/15	Spring break
	INFERENCE AND DECODING
T 3/20	16. Bayesian inference
R 3/22	17. Memory and hippocampus		HW 3 due, HW 4 out
T 3/27	18. Motor decoding and control
R 3/29	19. Perception inference
T 4/3	20. Neural implementation
R 4/5	21. Supervised Learning		HW 4 due. Hw 5 out
T 4/10	22. Semantic network
R 4/12	23. Emotion decoding
T 4/17	24. Concept learning
R 4/19	Spring Carnival
T 4/24	25. Quiz 2
R 4/26	26. Course review		HW 5 due
T 5/1	27. Project Presentation
R 5/3	28. Project Presentation		Term paper due
R 5/17	Final Grade due 6 p.m.

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