September, 2005
Psy
5038W, Fall 2005, 3 credits
Psychology Department , University
of Minnesota
Place: 150 Elliott
Hall
Time: 9:05-10:20 MW
Course home pages:
courses.kersten.org
Instructor: Daniel Kersten Office:
212 Elliott Hall Phone: 625-2589 email: kersten@umn.edu
Office hours: Mondays 10:20 to 11:20 or by appointment.
TA: Evangelos Theodoru Office:
N13 Elliott--Must call: 625 1337 for access) email: theo0027@UMN.EDU
Office hours: Mondays and Wednesdays 10:20 to 11:20.
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.
Readings
Grade Requirements
There will be a mid-term, final examination, programming assignments, as well as a final project. The grade weights are:
Assignment due BEFORE class start time (9:05 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.
(NOTE:
Many links below will remain broken until revised lecture material
is posted on the day of the lecture
--if
you want a preview, check
out lectures from 2003)
All lecture notes are in Mathematica Notebook and pdf format. You can download
the Mathematica notebook files below to view with Mathematica or MathReader
(which is free).
Date |
Lecture |
Additional Readings & supplementary material |
Assignments |
||
I.
|
1 |
Sep 7 |
Introduction (pdf file)|Mathematica notebook |
Mathematica
intro.nb |
|
2 |
Sep 12 |
The
neuron (pdf
file)| Mathematica
notebook |
|||
3 |
Sep 14 |
Neural Models, McCulloch-Pitt (pdf file)| Mathematica notebook | Koch, C., & Segev, I. (Eds.). (1998) (pdf) |
||
4 |
Sep 19 |
Generic neuron model (pdf file)| Mathematica notebook | |||
II. |
5 |
Sep 21 |
Lateral inhibition (pdf file)| Mathematica notebook | Hartline (1972) (pdf)
|
|
6 |
Sep 26 |
Matrices (pdf file)| Mathematica notebook | PS
1. Introduction to Mathematica ,
vectors, cross-correlation (pdf file) |
||
7 |
Sep 28 | Learning & Memory (pdf file)| Mathematica notebook | |||
III.
|
8 |
Oct |
Linear Associator (pdf file)| Mathematica notebook | ||
9 |
Oct 5 |
Sampling, Summed vector memory (pdf file)| Mathematica notebook | (See first part of Lecture 22 for review of probability and statistics). | ||
10 |
Oct 10 |
Non-linear networks, Perceptron (pdf file)| Mathematica notebook |
|
PS
2. Lateral inhibition - (pdf file) |
|
11 |
Oct 12 |
Regression, Widrow-Hoff (pdf file)| Mathematica notebook | |||
12 |
Oct 17 |
Multilayer feedforward nets, Backpropagation (pdf file)| Mathematica notebook |
Poirazi,Brannon & Mel (2003) (pdf) Williams (1992) (pdf) |
||
IV.
|
13 |
Oct 19 |
Science
writing (pdf) (Mathematica notebook) |
Gopen & Swan,
1990 (pdf)
|
PS
3. Perceptron (pdf file) |
14 |
Oct 24 |
MID-TERM | MID-TERM (16%) | ||
15 |
Oct 26 |
Networks and Visual Representation (pdf file)| Mathematica notebook | Carrandini, Heeger, Movshon (1996)(pdf) | ||
16 |
Oct 31 |
Neural Representation and coding (pdf file) Mathematica notebook | Sanger (2003) (pdf) Quiroga, R. Q., Reddy, L., Kreiman, G., Koch, C., & Fried, I. (2005).(pdf) |
||
17 |
Nov 2 |
Self-organization, Principal Components Analysis (pdf file)| Mathematica notebook | Supplement: ContingentAdaptation.nb | ||
18 |
Nov |
Discrete Hopfield network (pdf file)| Mathematica notebook | |||
19 |
Nov 9 |
Graded response Hopfield network (pdf file)| Mathematica notebook | Hopfield (1984) (pdf) | ||
20 |
Nov 14 |
Boltzmann machine (pdf file)| Mathematica notebook |
Sculpting the energy function, interpolation (pdf file)| Mathematica notebook) | PS
4 Backprop, Hopfield network (pdf file) |
|
21 |
Nov 16 |
Adaptive maps (pdf file)| Mathematica notebook | smallRetinaCortexMap.nb GraylefteyeDan.jpg |
Final project title & paragraph outline (2%) | |
22 | Nov 21 | Probability (pdf file)| Mathematica notebook |
Jordan, M. I. and Bishop. C. MIT Artificial Intelligence Lab Memo 1562, March 1996. Neural networks. | ||
V.
|
23 | Nov 23 | Generative
models,Bayes nets and inference (pdf file) Mathematica notebook |
Knill & Pouget (2004) (pdf) | |
24 | Nov 28 | Belief
Propagation (pdf) Mathematica notebook |
|||
25 | Nov 30 | EM (pdf) Mathematica notebook |
|||
26 | Dec 5 | Fisher's
linear discriminant (pdf) Mathematica notebook |
|||
27 | Dec 7 | Kalman
filter |
Complete Draft of Final Project (5%:) NOW DUE December 9 | ||
28 | Dec 12 | Bias/Variance, Wrap-up & |
Bias/Variance notes (pdf) | Drafts returned | |
Dec 14 | FINAL EXAM | FINAL STUDY GUIDE | FINAL EXAM (16%) | ||
Dec 19 | Final Revised Draft of Project (33%) | ||||
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 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:
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.
Some Resources:
Student Writing Support: Center for Writing, 306b Lind Hall andsatellite locations
(612.625.1893) http://writing.umn.edu.
Online Writing Center:http://www.owc.umn.edu
NOTE: Plagiarism, a form of scholastic dishonesty and a disciplinaryoffense, is described by the Regents as follows: Scholasticdishonesty means plagiarizing; cheating on assignments or examinations;engaging in unauthorized collaboration on academic work; taking,acquiring, or using test materials without faculty permission; submittingfalse or incomplete records of academic achievement; acting alone or incooperation with another to falsify records or to obtain dishonestlygrades, honors, awards, or professional endorsement; or altering,forging, or misusing a University academic record; or fabricating orfalsifying of data, research procedures, or data analysis.http://www1.umn.edu/regents/policies/academic/StudentConductCode.html
© 1998, 1999, 2001, 2003, 2005 Computational Vision Lab, University of Minnesota, Department of Psychology.