September 4, 2001

Introduction to Neural Networks
(Lecture Notes)

Place: 121 Elliott Hall (Computer Lab)
Time: 12:00-1:30 TTh

Course home page:
http://gandalf.psych.umn.edu/~kersten/kersten-lab/courses/Psy5038W/5038Syllabus.html
or find it through courses.kersten.org

Instructor: Daniel Kersten Office: 211 Elliott Hall Phone: 625-2589 email: kersten@umn.edu
Office hours: Thursday 1:30-2:30 or by appointment.

TA: Bruce Hartung Office 319 Elliott Hall Phone: 625-1337 email: hartung@cs.umn.edu
Office hours: Tuesday 1:30-3:00 or by appointment.

Course description. Introduction to large scale parallel distributed processing models in neural and cognitive science. Topics include: linear models, statistical pattern theory, Hebbian rules, self-organization, non-linear models, information optimization, and representation of neural information. Applications to sensory processing, perception, learning, and memory.

• Lecture notes
• Introduction to Neural Networks, James Anderson, MIT Press. 1995. (Appendices) (or Appendices)
• Gopen, G. D., & Swan, J. A., 1990. The Science of Scientific Writing. American Scientist, 78, 550-558.
• Introduction to Mathematica. (http://library.wolfram.com/tutorials/intro.nb)
  (For more information, see: Mathematica Tutorials. (http://library.wolfram.com/tutorials/)

• On reserve:
  • Penrose, A. M., & Katz, S. B. (1998). Writing in the Sciences: Exploring Conventions of Scientific Discourse. New York: St. Martin's Press, Inc.

  • American Psychological Association. (1994). Publication manual of the American Psychological Association (4th ed.). Washington, DC: American Psychological Association.

• Supplementary Reading
  
  *Bishop, C. M. (1995). Neural Networks for Pattern Recognition. Oxford: Oxford Univeristy Press.
  Blachman, N. (1992). Mathematica: A Practical Approach . Englewood Cliffs, NJ: Prentice Hall.
  Freeman, J. A. (1994). Simulating Neural Networks with Mathematica . Reading, MA: Addison-Wesley Publishing Company.
  *Gershenfeld, N. A. (1999). The nature of mathematical modeling. Cambridge ; New York: Cambridge University Press.
  Hertz, J., Krogh, A., &;Palmer, R. G. (1991). Introduction to the theory of neural computation (Santa Fe Institute Studies in the Sciences of Complexity ed.). Reading, MA: Addison-Wesley Publishing Company.
  Jordan, M. I. and Bishop. C. MIT Artificial Intelligence Lab Memo 1562, March 1996. Neural networks.
  Ripley, B. D. (1996). Pattern Recognition and Neural Networks . Cambridge, UK: Cambridge University Press.
  Wolfram, S. (1991). The Mathematica Book (4th ed.). Redwood City, CA: Addison-Wesley Publishing Company, Inc.
  *Recommended

  Also see mathsource.com, a resource site provided by www.wolfram.com the developers of Mathematica.
  The following link is particularly useful:
  0205-906: Simulating Neural Networks with Mathematica---Electronic Supplement

Grade Requirements

There will be a mid-term, final examination, programming assignments, as well as a final project. The grade weights are:

• Homework/programming : 28%
• Mid-term examination 16%
• Final examination: 16%
• Final project : 40% (three parts: 2%+5%+33%)

The programming assignments will use the Mathematica programming environment. No prior experience with Mathematica is necessary. List of Computer Labs at the University of Minnesota with Mathematica installed.

Assignment due BEFORE class start time (12:00 am) on the day due. You can use the downloaded Mathematica notebook for the assignment as your template, add your answers, and email your finished assignment to the TA. You can copy and paste any code bits you need from the Lecture notebooks. But of course, you cannot copy and paste code or any other answer materials from someone else.

Outline & Lecture Notes

(Revised lecture material will be posted on the day given--if you want a preview, check out lectures from 1999)

All lecture notes are in Mathematica Notebook and pdf format. You can either download the Mathematica files below to view (with MathReader 4, which is free) or to run (with Mathematica 4, which is not free--$139.95 for student license).

Final Project Assignment.

This course teaches you how to understand cognitive and perceptual aspects of brain processing in terms of computation. Writing a computer program encourages you to think clearly about the assumptions underlying a given theory. Getting a program to work, however, tests just one level of clear thinking. By writing about your work, you will learn to think through the broader implications of your final project, and to effectively communicate the rationale and results your results in words.

Your final project will involve: 1) a computer simulation and; 2) a 2000-3000 word final paper describing your simulation. For your computer project, you will do one of the following: 1) Devise a novel application for a neural network model studied in the course; 2) Write a program to simulate a model from the neural network literature ; 3) Design and program a method for solving some problem in perception, cognition or motor control. The results of your final project should be written up in the form of a short scientific paper, describing the motivation, methods, results, and interpretation. Your paper will be critiqued and returned for you to revise and resubmit in final form. You should write for an audience consisting of your class peers. You may elect to have your final paper published in the course's web-based electronic journal.

Completing the final paper involves 3 steps:

1. Outline. You will submit a working title and paragraph outline by the deadline noted in the syllabus. These outlines will be critiqued in order to help you find an appropriate focus for your papers. (2% of grade). (Consult with the instructor or TA for ideas well ahead of time).
2. Complete draft. You will then submit a complete draft of your paper. Papers must include the following sections: Introduction, Methods, Results, Discussion, and Bibliography. Use citations to motivate your problem and to justify your claims. Cite authors by name and date, e.g. (Marr & Poggio, 1979). Use a standard citation format, such as APA. Papers must be typed, with a page number on each page.Each paper will be reviewed with specific recommendations for improvement. (5% of grade)
3. Final draft. You will submit a final revision for grading. (33% of grade). The final draft must be turned in by the date noted on the syllabus. Students who wish to submit their final papers to be published in the class electronic journal should turn in both paper and electronic copies of their reports.

If you choose to write your program in Mathematica, your paper and program can be combined can be formated as a Mathematica notebook. See: Books and Tutorials on Notebooks.

Your paper will be critiqued and returned for you to revise and resubmit in final form. You should write for an audience consisting of your class peers.

© 1998, 1999, 2001 Computational Vision Lab, University of Minnesota, Department of Psychology.