Introduction to Neural Network Models in Cognitive Science (Psyc 3032/4254)
TTh 1:00 - 2:50, Fall 2001
Frontier Hall 158, University of Denver
Goals: How does the brain think? This course
will introduce you to the ideas and methods in computational cognitive
neuroscience that have been applied to answering this question.
Specifically, we focus on simulating cognitive and perceptual
processes using neural network models, which provide a bridge between
behavioral and biological levels of analysis. A core set of
computational principles based on well-established properties of
neural processing in the cortex will be introduced and used throughout
the course to account for a wide range of cognitive phenomena. This
focused and unified approach makes potentially difficult material
easier to learn, and allows us to explore more complex and interesting
phenomena. We start by understanding the basic computational and
biological properties of individual neurons and networks of neurons,
which give rise to basic processing mechanisms like spreading
activation, inhibition, and multiple constraint satisfaction. We then
discuss learning mechanisms (Hebbian and error-driven), which all
networks of neurons require to perform any reasonably complex task.
We then examine a range of cognitive phenomena within this framework,
including attention, memory, language, and higher-level cognition.
Requirements: The course is geared toward students with a strong background in psychology and/or biology. The course prerequisites are Introduction to Cognitive Neuroscience (Psyc 3031) and permission of the instructor. The models used in the course are mathematically based, but only algebra and some simple calculus-level concepts are required. The focus will be on intuitive and practical applications, not on theoretical derivations. Computer programming experience is not required, because the models are accessible via a graphical interface.
Text: O'Reilly, R. C., and Munakata, Y. (2000). Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain. MIT Press, Cambridge, MA.
Software: The software has been installed on the department
laptops and on Windows machines in the RIAS room, the Psychology
department computer cluster. You can download the software (from
http://psych.colorado.edu/~oreilly/cecn_download.html) to run
on your own machines. Most major platforms are supported: Linux,
Mac, Windows, Sun, SGI, HP.
Evaluation:
Your grade will consist of the following: 
The simulation exercises are in the text. You are strongly encouraged to run the simulations on your own, and you are required to write them up on your own. Aim for clarity and conciseness in writing up your answers; a sentence or two should suffice to answer many questions. (We'll cover ideal answers before the first homework is due.) You can skip certain questions in your homework write-ups (see schedule below), but you should still step through these exercises as you go through the chapter. (In some cases, this will be very useful for subsequent questions.) Homeworks are to be turned in at the beginning of class on the due date. Homeworks turned in late will be penalized 5% for each day after the due date, starting immediately after class has started (i.e., if you turn it in at the end of class on the day it's due, it is already 5% off).
Productive participation in class discussion is encouraged to help you get the most out of this course. Please also feel free to actively evaluate and provide feedback on the text (its content, clarity, etc.). You can communicate about any of this as a group by emailing pdp01@kore.psy.du.edu.
Class Schedule
To Run Simulations on Windows
Control Panel, choose Display and then Settings (the
rightmost option), and set the screen area.
Cog Neuro Sims).