[Overview] [Goals and Assessment] [Readings] [Software] [Syllabus]

85-419/719: Introduction to Parallel Distributed Processing

Spring 2008, Tue/Thu 10:30-11:50am, Doherty 1211

Instructor: David Plaut
Baker 254N, x85145
plaut@cmu.edu
     TA: Christine Watson
Baker 434, x87136
Office hours: Tu 1-2, We 3-4
cewatson@andrew.cmu.edu

Course webpage: http://www.cnbc.cmu.edu/~plaut/IntroPDP/


Announcements


Assignments


Overview

The goal of the course is to introduce the basic principles of parallel distributed processing (also known as connectionist or neural network modeling) and to illustrate how these principles provide insight into human perceptual, linguistic, and cognitive behavior. In addition, the course will cover some issues in neural and cognitive development, cognitive impairments due to brain damage, and some basic computational issues. The course also attempts to introduce the general practice of studying cognition through computational modeling and analysis. There will be computer simulation exercises in addition to readings. Homework assignments will generally require you to report the results of simulations you have carried out, to analyze these results, and to think critically about some issues raised in the readings. There will also be a final project that will typically involve simulation modeling.

The course is divided into five sections. The first three cover basic topics in parallel distributed processing. For each of these three sections, a homework assignment is handed out at the beginning of the section and is due at the end of the section. At the end of the third section (just before Spring Break), you will also be required to submit a one-page proposal outlining the final project you intend to carry out. This will be returned with feedback after Spring Break and you will be expected to get started on your project immediately thereafter. You should be on the lookout throughout the earlier sections of the course for topics or issues that you find particularly interesting and would like to pursue in more detail in a project. The fourth section focuses on applications from a wide range of perceptual, linguistic and cognitive domains, and will be followed by a take-home exam based on class lectures and readings. The final section (4 class meetings) will be devoted to brief oral reports from each student on the progress of their project. A 10-15 page paper based on the final project is due at the end of this last section. There is no final exam for the course.

In general, there are assigned readings for each lecture that are intended to prepare you to participate in the class discussion for that day. In addition, there may be optional background readings (listed in parentheses and marked with ``opt:'' in the Syllabus) that serve either as the basis for the lecture, to present an alternative point of view, or simply to make available to you relevant material that we won't have time to cover in class. Optional readings are also a good source of ideas for projects. There are no required readings on days when something is due, but you are still expected to attend class, hand in your homework, and draw on the material you have already learned in order to participate in the discussion.

[Back to Top]

Course Goals and Assessment

Below are the broad goals of the course and how each is assessed (listed in brackets). The grading in the class will be divided up as follows:

Homework 1: 10%
Homework 2: 15%
Homework 3: 20%
Project Proposal:   5%
Take-Home Exam: 15%
Final Project: 30%
Class Participation:   5%

Homeworks are due at the beginning of class on the date listed in the Syllabus (usually a Tuesday). Homeworks handed in late but before 5pm of the next day (usually a Wednesday) will be penalized by 5% (i.e., total points multiplied by 0.95); those handed in before 5pm of the following weekday (usually a Thursday, but a Monday if the homework was due on a Thursday) will be penalized 10%; those handed in later than that but before graded homeworks are returned will be penalized 20%. After other students' graded homeworks are returned, homeworks may be handed in for credit only with permission of the instructor. The 5% for class participation will be based on contributions to class discussions throughout the semester, and on the quality of the oral project report.

[Back to Top]

Readings

There is no required text for the course. All assigned and optional readings are available as downloadable pdf files from links in the Syllabus below. Other course materials (e.g., handouts, assignments, etc.) will be made available via links at the top of this web page.

The following texts contain some of the course readings and may be useful as general references:

[Back to Top]

Software

We will be using a software package called "Lens" (for Light Efficient Network Simulator), developed by former CMU CS graduate student Doug Rohde. Lens runs under both Windows and Unix-based systems (including Linux and Mac OS X). The main website for Lens is http://tedlab.mit.edu/~dr/Lens/.

If you're running one of the following operating systems, you can download a file containing a precompiled version of Lens.

If you're not using one of these platforms, or if for some reason the precompiled version for your platform doesn't work (let me know if this happens), you'll need to download Lens and compile it yourself. Instructions for how to do this can be found at http://tedlab.mit.edu/~dr/Lens/installing.html.

After installing Lens, you should look at the online manual at http://tedlab.mit.edu/~dr/Lens/, particular the instructions under "Running Lens" and the Tutorial Network under "Example Networks". The precompiled versions of Lens come with a offline (local) copy of the manual that can be accessed by pointing your web browser at Manual/index.html in the Lens directory. Those installing Lens from scratch can also download an offline copy of the manual from http://tedlab.mit.edu/~dr/Lens/Dist/lens-manual.tar.gz. Just move this into your Lens directory and run "tar xzf lens-manual.tar.gz".

[Back to Top]

Syllabus

This syllabus is subject to change throughout the course, so be sure to revisit this web page frequently.


Section 1: Processing and Constraint Satisfaction

Jan 15 (Tue): Overview and basic principles (slides) [HOMEWORK 1 HANDED OUT] [Install Lens (see Software section)]

Jan 17 (Thu): Lens tutorial

Jan 22 (Tue): Constraint satisfaction

Jan 24 (Thu): Schema theory

Jan 29 (Tue): Psychological implications [HOMEWORK 1 DUE]


Section 2: Simple Learning and Distributed Representations

Jan 31 (Thu): Hebb and Delta rules (slides) [HOMEWORK 2 HANDED OUT]

Feb 5 (Tue): Pattern association (slides)

Feb 7 (Thu): Distributed representations

Feb 12 (Tue): Psychological implications [HOMEWORK 2 DUE]


Section 3: Learning Internal Representations

Feb 14 (Thu): Back-propagation (slides) [HOMEWORK 3 HANDED OUT]

Feb 19 (Tue): Temporal learning and recurrent networks

Feb 21 (Thu): Generalization and overfitting

Feb 26 (Tue): Contrastive Hebbian learning

Feb 28 (Thu): Unsupervised learning (slides)

Mar 4 (Tue): Reinforcement learning and forward models [lecture by C. Watson] (slides)

Mar 6 (Thu): Psychological implications (slides) [HOMEWORK 3 DUE]

Mar 11, 13: NO CLASS (Spring Break)


Section 4: Applications

Mar 18 (Tue): Memory and the hippocampus (slides) [PROJECT PROPOSAL DUE]

Mar 20 (Thu): High-level vision and attention [lecture by M. Behrmann] (slides)

Mar 25 (Tue): Cognitive development (slides)

Mar 27 (Thu): Language: Morphology (slides)

Apr 1 (Tue): Language: Word reading (slides)

Apr 3 (Thu): Language: Sentence processing (slides)

Apr 8 (Tue): Semantics (slides)

Apr 10 (Thu): Routine action (slides) [TAKE-HOME EXAM HANDED OUT (covering Mar 21 to Apr 13)]

Apr 15 (Tue): Cognitive control [lecture by C. Watson] [TAKE-HOME EXAM DUE]

Apr 17 (Thu): NO CLASS (Spring Carnival)


Section 5: Project Progress Reports

Apr 22 (Tue): Arizpe, Doersch, Doyle, Flynn, Lundin, Maas, Whitney, Zachariou
Apr 24 (Thu): Austin, Farmer, Kramer, Lim, Navia, Sandler, Sheehan, Wen
Apr 29 (Tue): Comer, Hwang, Iwanaga, Klionsky, McCortney, Sampson, Scozio, Stedenfeld
May 1 (Thu): Bates, Danker, Kanter, Liu, Nowak, Mou, Shen, Taylor
May 2 (Fri) 5pm: PROJECT PAPER DUE

[Back to Top]