Introduction to large scale parallel distributed processing models in neural and cognitive science. Topics include: linear models, Hebbian rules, self-organization, non-linear models, information optimization, and representation of neural information. Applications to sensory processing, perception, learning, and memory.
4 cr; The formal prerequisites are: Math 3261, Psy 3031 or 5061, or #.
The most important prerequisite is some background in linear algebra (vectors and matrices) and calculus. It is OK if your vectors and matrices are rusty, because we will review the basic facts of linear algebra that we need.
Syllabus 1999
Lecture notes Spring 1999
Programming assignments 1999
Last year's material - 1997-98:
Lecture notes Spring 1998
Programming assignments 1998
Mathematica: Wolfram Research Home page (Mathematica) | Calculus & Mathematica
Neural network sites: David MacKay's home page | Gatsby Computational Neuroscience Unit
Neural networks frequently asked questions: NNs FAQ site
Vision-related sites: Illusion Works homepage | Dictionary of Vision terms: Visionary
Questions?
Contact:
Prof. Daniel Kersten, 211 Elliott Hall
Phone: 625-2589
Email: kersten@eye.psych.umn.edu
Kersten Lab | Vision Lab | Psychology Department | University of Minnesota
© 1998 Computational Vision Lab, University of Minnesota, Department of Psychology.