| Computational
Models of Cognition
Fall
2005
Course Description
This course will introduce
a range of computational techniques for the modeling of cognitive processes.
We will explore the role of modeling in cognitive science, and the explanatory
power of a number of symbolic, statistical and neural network models
in a variety of empirical domains, including language, categorization
and reasoning.
Syllabus: pdf
| Topic |
Labs |
Materials |
| Symbolic
Modeling |
Intro
to Prolog |
Lab
0 (due 9/20): Getting Started with Prolog. Choose one
assignment file (windows, unix)
as appropriate for your computer, as well as the prolog
data file. |
Software:
SWI-Prolog
Tutorials:
Learn Prolog Now!, prolog
:- tutorial
Prolog examples: Map
coloring |
| Semantic
Networks |
Lab
1 (due 9/30). You'll also need the prolog file semnet.pl. |
Reading:
Modeling Memory (from P. Scott and
R. Nicolson, Cognitive Science Projects in Prolog, LEA,
1991). |
| Wordnet |
Lab
2 (due 10/4). For problem 3 of this lab, you'll need the prolog
file wn_ui.pl. |
Reading:
Five papers on wordnet
Download
prolog wordnet (documentation)
Wordnet website |
| Grammars
and Parsing (slides1, slides2) |
Lab
3 (due 10/28).
You will need lab3-bottom-up.pl
and grammar-bottom-up.pl. To
do this problem set, you will find it helpful to read Shieber's
(1983) paper,
as well as section 4.2 of Pereira and Shieber's book. |
Grammar
examples:
1. simple cfg
2. cfg with difference lists
3. extracting structure
Parsers:
1. top-down parser
2. bottom-up parser (with
structure)
3. grammar for parsers (with
structure)
Reading:
Shieber (1983) Sentence
Disambiguation by a Shift-Reduce Parsing Technique, 21st Annual
Meeting of the Association for Computational Linguistics.
Pereira and Shieber
(1987) Prolog
and Natural Language Analysis |
| Connectionist
Modeling |
Basics
(slides1,slides2) |
Lab
4 (due 11/14) For this lab, you'll be working through Colin
Phillips' nicely annotated lab 2a (from his psycholinguistics course).
|
Software:
tlearn simulator (Note
that the macintosh version runs either on OS9 or under Classic.
For help on running tlearn under windows, see these
notes.)
Reading: Plunkett and
Elman (1997) Exercises
in Rethinking Innateness (chapters 1-4) |
| Past
tense and Lexical development (slides) |
Lab
5 (due 11/22)
To do this lab, you'll need the files contained in this
archive. |
Reading:
Pinker (1985) Why
the Child Holded the Baby Rabbits: A Case Study in Language Acquisition.
In L. Gleitman & M. Liberman (eds) Language: An Invitation to
Cognitive Science, Vol 1 (2nd edn.), 107-133. |
| Syntax
and Simple Recurrent networks (slides) |
|
Reading:
Elman, J. L. (1991). Distributed
representations, simple recurrent networks, and grammatical structure.
Machine Learning, 7, 195-224.
Lewis, J.D., &
Elman, J.L. (2001). Learnability
and the statistical structure of language: Poverty of stimulus
arguments revisted.Proceedings of the 26th Annual Boston University
Conference on Language Development.
Frank, R., Mathis,
D, and W. Badecker (2004) The
acquisition of anaphora by simple recurrent networks. Manuscript. |
| Statistical
Modeling |
Intro
to probability |
Lab
6 (due 12/16). |
Goldsmith,
J., Probability
for linguists. |
Rational
Analysis (slides) |
|
Oaksford,
M. and Chater, N. (1994) A
rational analysis of the selection task. Psychological Review
101:608-631. |
Word
Segmentation and Language Models (slides)
|
|
Brent,
M. (1999) Speech
segmentation and word discovery. Trends in Cognitive Sciences
3:294-301. |
| Stochastic
Grammars |
|
Jurafsky,
D. (1996) A
probabilistic model of lexical and syntactic access and disambiguation.
Cognitive Science 20:137-194. |
|
