15th International Florida Artificial Intelligence Research Society Conference
May 16-18, 2002
Special Track : "Categorization and Concept Representation :
Models and Implications"
This track seeks to bring together researchers working on issues related to categorization and concept representation in the areas of Artificial Intelligence and Cognitive Psychology.
Categorization is the process by which distinct entities are treated as equivalent. It is one of the most fundamental and pervasive cognitive activities. It is fundamental because categorization allows us to understand and make predictions about objects and events in our world. The problem of understanding what criteria are used to group together entities in the same category is indeed central in categorization. Though most works on this topic have proposed that perceptual or structural similarity is the "glue" that binds objects of a same category, some psychologists have claimed that similarity is insufficient to account for the acquisition and use of categories and have proposed more abstract forms of criteria that make categories coherent and give them a kind of homogeneity in terms of the entities that belong to them.
The different new proposals psychologists have suggested are that objects are grouped together because they facilitate a common goal or serve the same function. Some categories are viewed as coherent because they rest on a theory which explains the commonalities of their elements. Similarity and goals, on the one hand, and theories, on the other hand, have not been paid the same attention in computational models of categorization. Similarity-based models abound and the notion of categorization goals has also been exploited in computational models. On the other hand, the notion of an underlying theory that makes a category coherent is just beginning to be further analyzed and specified. New computational models of categorization reflecting this new tendency are thus expected.
The representation of concepts that a categorization system generates is of course intimately tied to the criteria this system uses to group entities into categories, so along with new models of categorization, we expect to see the emergence of new models of concept representation apart from the classical ones deriving from the Aristotelician, the Prototypical and the Exemplar Views. The representation of the entities to categorize also plays an important part in the categorization process. In particular, the context in which the entities occur may influence the way they are classified.
The purpose of this track is to bring fresh insights concerning a perhaps revisited notion of similarity, the way goals of categorization influence this process, how the notion of the theory of a concept can be formalized and implemented in computational models of categorization and the implications those elements may have on the representation of concepts.
The contributions to this track may be situated in either symbolic or connectionist approaches to categorization.
Contributions in the following sub-topics would be welcomed :
- Computational models of similarity,
- Computational models of theory-based categorization,
- Computational models of similarity-based categorization,
- Computational models of human categorization,
- Models of concept representation which are relevant to the process of categorization,
- Models of concept representation and elicitation,
- Formalization of the notion of theory which underlies a category,
- Formalization of the context of occurrence of the entities to be categorized and their influence on the categorization process.
This list is not exclusive provided that the contributions are relevant to the definition of the track specified above.
Paper Review and Publication
Only full papers will be considered for the track. Submitted papers will be reviewed by two program committee members. An author for an accepted paper is expected to present the paper in the track. Papers accepted for the track will be published in the FLAIRS 2002 Conference Proceedings.
The best papers will be invited for modification, extension and submission to a special issue in JETAI (Journal of Experimental and Theoretical Artificial Intelligence).
Submission Intention Deadline : September 19, 2001
Paper Submission Deadline : November 15, 2001
Notification of Acceptance-Rejection : January 10, 2002
Camera Ready Copy Due : March 4, 2002
Journal Invitation : February 10, 2002
Journal Paper Due : May 10, 2002
Conference Dates : May 16-18, 2002
David W. Aha, Navy Center for Applied Research in AI, Washington, USA
Ralph Bergmann, University of Kaiserslautern, Germany
Max Bramer, University of Portsmouth, UK
Colette Faucher (Chair), University of Aix-Marseille III, France
Paolo Frasconi, University of Florence, Italy
Robert L. Goldstone, Indiana University, USA
James Hampton, City University, London, UK
David Leake, Indiana University, USA
Bradley C. Love, University of Texas, USA
Paul Mc Kevitt, University of Ulster, Northern Ireland
Ryszard S. Michalski, George Mason University, USA
Philip Resnik, University of Maryland, USA
Lance J. Rips, Northwestern University, USA
Steven A. Sloman, Brown University, USA
Paper Submission Information
Authors must submit an electronic copy of their complete manuscript of no more than 5 pages. All submissions must be original work.
The review will be blind. Author names and affiliations are to appear ONLY on a separate cover page. The presenter (if different) from the first author must be specified on that cover page. All appropriate contact information must be mentioned for each author (e-mail, phone, fax, etc.).
Papers must be written using MS Word, RTF or PDF formats according to AAAI's standard format for authors.
All submissions must be sent in electronic form to :
[log in to unmask] and [log in to unmask]
For any problem or question, please contact the track chair, Colette Faucher, at : [log in to unmask] or [log in to unmask].
FLAIRS 2002 Website