15-386/686 Neural Computation

Carnegie Mellon University

Spring 2011 School of Computer Science

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) Mellon Inst. Rm 115 tai@cnbc.cmu.edu (412-268-1060)
  GHC 8017 (Tu/Thur 4:30-5:30 pm)  
Kyung-Ah Sohn (TA) M: 4:30-5:30 GHC 8127 ksohn@cs.cmu.edu
Amber Xu W: 2:00-3:00 West-wing clusters axu@andrew.cmu.edu
* Time and Location of Office Hour subject to change.

Recommended Textbook

Classroom Etiquette

Grading Scheme

Evaluation% of Grade
4 Assignments 50
Quiz 1 10
Term Project 25
Quiz 2 15
686 additional requirements

Homework Assignments

Late Policy

Term project

Examinations

Additional Requirement for 15-686 students

Additional Requirement for 86-686 students

Final Grade Assignment

Laboratory/Help Sessions

Syllabus

&  
Date Lecture Topic Relevant Readings Assignments
  NEURONS AND SYNAPSES    
T 1/11 1. Introduction ch  
R 1/13 2. Neurons ch  
T 1/18 3. Spikes ch  
R 1/20 4. Models ch Matlab tutorial (5:30-7:00) Hunt
T 1/25 5. Synapses ch HW 1 out
W 1/26   ch Matlab tutorial /Help : 5:30-7:00 (Mabaran at Hunt)
R 1/27 6. Randomness ch  
T 2/1 7. Sensory System ch  
W 2/2   ch 386 Help session 5:30-7:00 (Amber)
R 2/3 8. Tunings and Receptive fields ch HW 1 due. HW 2 out;
  CIRCUITS AND SYSTEMS    
T 2/8 9. Learning rules (Munro) ch  
W 2/9   ch 385 Help session 5:30-7:00 (Ben)
R 2/10 10. Representational learning ch  
M 2/14     386 Help session 5:30-7:00 (Kyung-Ah)
T 2/15 11. Functional Architecture ch  
R 2/17 12. Network dynamics (Ermentrout) ch HW 2 due. HW 3 out
T 2/22 13. Supervised Learning ch  
W 2/23   ch 385 Help session 5:30-7:00 (Mabaran)
R 2/24 14. Unsupervised Learning ch  
T 3/1 Quiz 1 ch  
W 3/2     386 Help session 5:30-7:00 (Amber)
R 3/3 15. Self-organizing maps   Project ideas
S 3/5      
M 3/7 Midterm Grade due 6 p.m.    
T 3/8 Spring break    
R 3/10 Spring break    
  DECODING AND INFERENCE    
T 3/15 16. Classification and inference ch HW 3 in, HW 4 out
W 3/16   ch 385 Help session 5:30-7:00 (Mabaran, Ben)
R 3/17 17. Semantic network decoding ch
M 3/21     386 Help session 5:30-7:00 (Kyung-Ah)
T 3/22 18. Hippocampus decoding ch  
R 3/24 19. Motor system (Chase) ch  
T 3/29 20. Visual decoding ch HW4 due
R 3/31 21. Cortical Inference ch
T 4/5 22. Functional Connectivities ch  
R 4/7 23. Concept Learning (Kemp) ch  
T 4/12 24. Population codes ch Project midterm (3)
R 4/14 Spring Carnival    
T 4/19 25. Decision making  
R 4/21 26. Project Presentation    
T 4/26 27. Project Presentation    
R 4/28 27. Quiz 2   Term paper and project due (20)
M 5/2 (5:30-8:30 pm) GHC 4215 Final Exam Day: (Quiz 2) & Project Presentation    
R 5/12 Final Grade due 6 p.m.    

Questions or comments: contact Tai Sing Lee
Last modified: Jan 9, 2011, Tai Sing Lee