Courses in previous years:
[ 2002
| 2001
| 2000
| 1999
]
T-61.184 Special course in Information Science I (4 cr) (L)
Statistical and adaptive approaches to conceptual modeling
Organisers: prof. Timo Honkela, D. Sc. Krista Lagus, and M. Sc. Jaakko Särelä
Semester: Autumn 2003
Credit points: 4 cr
Place: First three lectures are held in
Lecture hall T4,
computer science building, Konemiehentie 2, Otaniemi, Espoo
Place for subsequent meetings will be given during the course.
Time: Thursdays 14-16, starting from September 18
Language: English (or Finnish)
Homepage: http://www.cis.hut.fi/Opinnot/T-61.184/
Detailed course brochure
Seminar course description
Conceptual modeling is a task which has traditionally been
conducted "by hand". In artificial intelligence knowledge engineers
have written descriptions of various domains using formalisms based on
predicate logic and other symbolic representations such as semantic
networks and rule-based systems. The development of expert systems in
1980s was a notable example of such efforts. As a modern, related
attempt the Semantic Web can be mentioned.
An alternative approach is to consider both perceptual and
linguistic domains as well as the potential benefits of adaptive
models. There is a growing body of research based on pattern
recognition techniques and adaptive techniques that attempt to solve
the problem of how to model conceptual knowledge using computers.
Course structure
The course begins with three presentations in which the overall theme
is introduced in an interdisciplinary manner. A list of topics is
given and the participants form groups that will work on their topic
guided by one or more senior researchers. The senior researchers have
prepared abstracts for the articles as well as a preliminary list of
references that is relevant for the topic. Each group will write a
scientific article which is the requirement for passing the
course. Each article will be submitted either to a scientific
conference or to a journal The groups will present their intermediate
results during the autumn and present questions to be handled in the
general discussion.
Timetable
- 18 September 2003
Timo Honkela, Krista Lagus and Jaakko Särelä:
Conceptual modeling: variety of approaches, philosophical and
cognitive aspects.
Preliminary list of topics is introduced.
- 25 September 2003
Jaakko Särelä, Timo Honkela and Krista Lagus:
Overview of statistical and adaptive
methods for conceptual modeling.
Final list of topics with abstracts.
- 2 October 2003
Krista Lagus, Jaakko Särelä and Timo Honkela:
Empirical methods in conceptual modeling.
Forming the groups.
- From 9 October to 27 November 2003
Group meetings and joint meetings.
- 4 December 2003
First Miniconference.
- 16 January 2004
Second Miniconference
Prof. Peter Gärdenfors' visit
and guest lecture
- 19/20 January 2004
Choice of reviewers for each paper.
- 21 January 2004
Deadline for papers to be reviewed. Papers are send to timo.honkela@hut.fi
to be distributed to the reviewers (first four papers sent).
- 30 January 2004
Deadline for reviews (first four).
- 13 February 2004
Deadline for papers that will be included in a technical report
(either in tex or MS Word format).
Papers will also be submitted elsewhere based on each group's own
decision.
Prerequisites for attending
This special course is intended mainly for graduate students, however,
advanced undergraduate students may also be admitted (please, contact
Jaakko Särelä, with reasons
to be considered).
Each participant is expected to have reasonably advanced understanding
of either the methodological basis (statistical and adaptive methods)
or the domain of interest (e.g., conceptual modeling in computer
science or artificial intelligence, area of semantics and pragmatics
in linguistics, language understanding in psychology, or epistemology
in philosophy).
Students, e.g., from the following disciplines and areas are welcome:
- Language Technology major (Kieliteknologian pää-/sivuaine),
Computer and Information Science, and
Information Processing Science at Helsinki University of Technology,
- KIT (Kieliteknologian opetuksen verkosto, network
of language technology education in Finland),
- cognitive science, general linguistics, computer science, and
theoretical philosophy at University of Helsinki, and
- Media Lab of University of Art and Design.
Successful participation does not require specific mathematical
modeling or programming skills.
Requirements for passing the course
Course will be graded as accepted / failed. Active participation in
producing a scientific article in a group is a requisite for passing
the course.
Signing up for the course
HUT students: fill the form at WWW
Topi (preferred) OR send email to Jaakko Särelä. Students from
other universities: send email to Jaakko Särelä. If you are
unable the follow the above procedure, please sign up at the first
lecture.
More information
For more information, please contact Prof. Timo Honkela.