Course page

VS298: Neural Computation

Note: new course number – VS265

This course changed its number to VS265 in 2010, so please look there if you’re interested in taking it. Below is an archival copy of the last time it was taught in Fall 2008. And here’s the archive of the first time the course was taught in Fall 2006.

Course description

This course provides an introduction to the theory of neural computation. The goal is to familiarize students with the major theoretical frameworks and models used in neuroscience and psychology, and to provide hands-on experience in using these models. Topics include neural network models, supervised and unsupervised learning rules, associative memory models, probabilistic/graphical models, and models of neural coding in the brain.

This course differs from MCB 262, Advanced Topics in Systems Neuroscience, in that it emphasizes the theoretical underpinnings of models – i.e., their mathematical and computational properties – rather than their application to the analysis of neuroscientific data. It is offered in alternate years, interleaving with MCB 262. Students interested in computational neuroscience are encouraged to take both of these courses as they complement each other.

Instructors

Bruno Olshausen

  • Email: link
  • Office: 570 Evans
  • Office hours: TBD

Amir Khosrowshahi, GSI

  • Email: link
  • Office: 567 Evans
  • Office hours: Tuesday 5-6pm

Lectures

  • Location: Evans 508-20
  • Times: Tuesdays & Thursdays, 3:30-5:00. First meeting is Tuesday, September 2nd.

Enrollment information

  • Open to both undergraduate and graduate students, subject to background requirements specified below.
  • Telebears: {CCN, Section, Units, Grade Option} == {66487, 02 LEC, 3, Letter Grade}

Email list and forum

  • Please subscribe to the class email list here. The list name is vs298-students.
  • A bulletin board is provided here for discussion regarding lecture material, readings, and problem sets. Code required for signup will be distributed to the class email list.

Grading

Based on weekly homework assignments (60%) and a final project (40%).

Required background

Prerequisites are calculus, ordinary differential equations, basic probability and statistics, and linear algebra. Familiarity with programming in a high level language such as Matlab is also required.

Textbooks

  • [HKP] Hertz, J. and Krogh, A. and Palmer, R.G. Introduction to the theory of neural computation. Amazon
  • [DJCM] MacKay, D.J.C. Information Theory, Inference and Learning Algorithms. Available online or Amazon
  • [DA] Dayan, P. and Abbott, L.F. Theoretical neuroscience: computational and mathematical modeling of neural systems. Amazon

HKP and DA are available as paperback. Additional reading, such as primary source material, will be suggested on a lecture by lecture basis.