15-386/686 Neural Computation

Carnegie Mellon University

Spring 2022

Course Description

Neural Computation is an area of interdisciplinary study that seeks to understand how the brain learns and computes to achieve intelligence. It seeks to understand the computational principles and mechanisms of intelligent behaviors and mental abilities -- such as perception, language, motor control, decision making and learning -- by building artificial systems and computational models with the same capabilities. This course explores computational principles at multiple levels, from individual neurons to circuits and systems, with a view to bridging brain science and machine learning. It will cover basic models of neurons and circuits, computational models of learning, memories and inference in real and artifical systems. Concrete examples will be drawn mostly from the visual system, with emphasis on relating current deep learning research and the brain research, from hierarchical computation, attention, recurrent neural networks, to reinforcement learning. Students will learn to perform quantitative analysis as well as computational experiments using Matlab and deep learning platforms. No prior background in biology or machine learning is assumed. , Prerequisites: Basic knowledge of matrix, linear algebra, basic calculus (partial differential equations), probability and statistics are required. 15-100, 21-120 or permission of instructor. 21-241 preferred but not required.

Course Information

Instructors Office (Office hours) Class zoom link Email (Phone)
Tai Sing Lee (Professor) Friday 10:00-11:00 a.m. taislee@andrew.cmu.edu
Tianqin Li (TA) Tuesday and Wednesday 8-9 p.m tianqinl@andrew.cmu.edu
Sicheng Dai (TA) Tuesday 5-6 pm. Friday 4-5 p.m. sichengd@andrew.cmu.edu
Macardle Meng Monday 4-5 p.m Wed 4-5 p.m. mmeng@andrew.cmu.edu
Chloe Chen Monday 6-7 p.m. Thursday 7-8 p.m. tcchen@andrew.cmu.edu

Recommended Supplementary Textbook

Classroom Etiquette

386 Grading Scheme

Evaluation% of Grade
Assignments 70
Midterm 10
Final Exam 20
Optional term paper/project (Replacement of 1 HW ) 12
  • Grading scheme: A: > 88% B: > 75%. C: > 65% .
  • 686 Grading Scheme

    Evaluation% of Grade
    Assignments 70
    Midterm 10
    Final Exam 20
    Weekly Journal Club (Friday - reading / presentations) Required No credit.
    Term project You may use a term project to replace Journal Club
    Term project + journal club Term project can replace two problem sets
  • Grading scheme: A: > 88% B: > 75%. C: > 65% .
  • If the term project to replace two problem sets, the term project will be graded and awarded up to 28 points, otherwise it will be graded as good, pass or fail. "Good" + 88% are needed for an A.
  • Assignments

    Term Project


    Late Policy


    Date Lecture Topic Relevant Readings Assignments
      Part 1: Neurons and Synapses    
    W 1/19 1. Introduction and Overview NIH Brain Facts (chapter 1)  
    F 1/21 Math and Matlab Tutorial (optional) Trappenberg Math Appendix  
    M 1/24 2. Neurons and Membranes Trappenberg Ch 1.1-2.2
    W 1/26 3. Spikes and Cables Trappenberg Ch 2 (C) HW1 out
    M 1/31 4. Synapse and Dendrites Trappenberg Ch 3.1, 3.3  
    W 2/2 5. Synaptic plasticity Trappenberg Ch 4 Abbott and Nelson (2000)  
    M 2/7 6. Hebbian Learning Trappenberg Ch 4, HPK Ch 8  
    W 2/9 7. Logical Computation Trappenberg 3.1,3.5 F. Rosenblatt - Perceptron. McCulloch and Pitts (1943) HW2 out, HW1 in
      Part 2: Representation and Computation    
    M 2/14 8. Principal Component Analysis Oja (1982)  
    W 2/16 9. Source Separation Foldiak (1990)  
    M 2/21 10. Sparse Coding Olshausen and Field (1997) (2004)  
    W 2/23 11. Deep Belief Net Trappenberg Ch 10.3 Hinton and Salahutdinov (2006) HW3 out. Hw2 in.
    M 2/28 12. Computational Maps HPK Ch 9. Trappenberg 7.1-7.2 Kohonen (1982)  
    W 3/2 Midterm  
    3/4-3/11 Midsemester and Spring break. No Journal Club March 7. Midterm grade due
      PART 3: Neural Networks    
    M 3/14 13. Visual System Trappenberg 5.1. Van Essen et al (1992) Fellman and Van Essen ( 1991)  
    W 3/16 14. Markov Network Marr and Poggio (1976) Samonds et al. (2013) Wang et al. (2018) Term Project Proposal in
    M 3/21 15. Attractor network and Memory Trappenberg Ch 8. Ch 9.4 Hopfield and Tank (1986)  
    W 3/23 16. Cue Integration   HW4 out, HW3 in
    M 3/28 17. Neural network (MLP) Trappenberg Ch 6, 10.1. Fukushima (1988), Krizhevsky et al. (2012)  
    W 3/30 18. Convolutional Neural Networks Zeiler and Fergus (2013) LeCun, Bengio and Hinton (2015)  
    M 4/4 19. Deep Network and the Brain Yamins and DiCarlo (2016) Maheswaranathan et al. (2018) Lillicrap et al. (2016)  
    W 4/6 20. Biological Plausible Learning Arrout et al. (2019), Guerguiev et al. (2017) HW5 out, HW4 in.
    F 4/9 Carnival No Journal Club    
    M 4/11 21. Hierarchical Inference Mumford (1992) Rao and Ballard (1998) Lee and Mumford (2003)  
    W 4/13 22. Attention and Self-Attention Trappenberg Ch 10. Vaswani et al. (2017) Lindsay (2020) Knudsen (2007)  
    M 4/18 23. Prediction and Surprise Trappenberg Ch 10. Lotter et al (2016), Colah (2015) Rao (2015)  
    W 4/20 24. Probabilistic Inference Weiss et al. (2002). Ma et al. (2006) Kersten and Yuille (2003) HW 5 in.
    M 4/25 25. Inference Mechanisms Orban et al. (2016). Shivkumar et al. (2019)  
    W 4/27 26. Reinforcement Learning Trappenberg. Ch 9. Niv (2009), Montague et al. (1996)  
    M 5/2 Final Exam Period    
    Th 5/12 Final Grade due 4 p.m.    

    Journal Club 2022

    Week 3 (2/18): Retinal Computation

    Week 4 (2/25): Sparse Coding

    Supplementary Reading List foru Journal Club (more to come)

    Logical computation in Neurons

    Biological Neural Circuits

    Neural Network models of Neural Circuits

    Sparse Coding on computation and memory

    Reinforcement Learning

    Biological Plausible Deep Learning Algorithms

    Casual inference

    Inverse Rational Control

    Spiking Bayesian Circuit

    Curiosity and Imagination

    Reinforcement Learning and Song Birds



    Glia and their functions

    Questions or comments: contact Tai Sing Lee
    Last modified: spring 2022, Tai Sing Lee