15-386/686 Neural Computation

Carnegie Mellon University

Spring 2015

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, neural encoding and decoding strategies, neural networks and learning, signal processing and system analysis, statistical learning and probabilistic inference. Concrete examples will be drawn from the visual system and the motor system, including deep learning and brain computer interface. 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 6025 M 3-4, MI 115 (occasionally GHC 6025) Thur. 2:30-3:30	tai@cnbc.cmu.edu (412-268-1060)
Jack Liao (TA)	Tue 6:30-7:30. Fri. 1:30-3:00 Citadel teaching commons, 5th floor of GHC.	jackliao07@gmail.com

Class location and time: GHC 4102 M/W 1:30 p.m - 2:50 p.m.
Website: http://www.cnbc.cmu.edu/~tai/nc-15.html (course info)
Blackboard: http://www.cmu.edu/blackboard/ (Both 386/686 students should use 386 BB for access of course materials and announcements.

Classroom Etiquette

Turn OFF your laptop, cell phones or any other electronic devices in the classroom please.

Grading Scheme

Evaluation	% of Grade
Assignments	60
Quiz 1	10
Final Exam + (maybe Quiz 2)	30
Term project (optional 386, required for 686)	letter grade only

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

Assignments

6 Matlab programming or 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 one quiz or assignment grade, and/or to contribute to up to 50% of their final exam grade. Collaboration is allowed, but in this case, it can't be used to replace homework or quiz grades, but can contribute to the final, i.e. the final exam will only count for 15 points for these students. 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. Collaboration is allowed, but the project will need to be approved by the instructor. The project grade will only receive letter grade (A,B,C). A 686 student will receive an A if his project a A or B AND his "386" score equals or greater than 88%.

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 six days grace for submitting their assignments late without penalty. This six-day grace can be used all together for one assignment, submitting one assignment 6 days late, or used separately for different assignments, submitting each assignment one day late. Blackboard submission after noon on the due day is considered late.
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 % (same as 386) and getting an A or B for their term projects.

Syllabus

Date	Lecture Topic	Assignments
	LEARNING AND REPRSENTATION
M 1/12	1. Intro
W 1/14	2. Brain facts
M 1/19	3. MLK Day no class
W 1/21	4. Neurons	HW1 out
M 1/26	5. Matlab tutorial *
W 1/28	6. Spikes
M 2/2	7. Synapses and plasticity
W 2/4	8. Hebbian learning	HW 1 in. HW 2 out
M 2/9	9. Principal component analysis
W 2/11	10. Tunings and Frequency Analysis
M 2/16	11. Primary visual cortex
W 2/18	12 Sparse coding	HW2 in, HW3 out.
M 2/23	13. Quiz 1
W 2/25	14. ICA applications
M 3/2	15. Computational maps
W 3/4	16. Kohonen self-organizing maps	HW 3 in, HW 4 out
M 3/9	Midterm Grade due
M 3/9	Spring break
W 3/11	Spring break **
M 3/16	17. Neurons as classifiers	Project proposal due
W 3/18	18. Multi-layer perceptron and BP	HW 4 in, HW 5 out
M 3/23	19. Hierarchy and Neocognitron
W 3/25	20. Convolution nets and HMAX
M 3/30	21. Markov random fields (segmentation)	Quiz 2
W 4/1	22. Brain as Boltzmann machines	HW 5 in, Hw 6 out
M 4/6	23. Deep beief nets
W 4/8	24. Feedback and Varieties of Models
M 4/13	25. Compositional Concept Models
W 4/15	26. Attention mechanisms (oscillations)	HW 6 (choice) out ;
M 4/20	27. Complmentary Memory Systems	&nbpsp;
W 4/22	28. From Perception to Action
M 4/27	29. Project Presentation
W 4/29	30. Project Presentation	Term paper due
F 5/1	Reading period
Th 5/14	Final Grade due 4 p.m.

Questions or comments: contact Tai Sing Lee
Last modified: Jan 9, 2015, Tai Sing Lee