Constructing Conceptual Spaces for Novel Associations
Inhaltsverzeichnis
Reference
Kazjon Grace, Rob Saunders, John Gero: Constructing Conceptual Spaces for Novel Associations. In: Computational Creativity 2010 ICCC 2010. 120-129.
DOI
Abstract
This paper reports on a system for computational analogy- making based on conceptual spaces. The system constructs conceptual spaces that express the relationships between concepts and uses them to build new associations. A case for this conceptual-space driven model of association making is made, and its advantages and disadvantages are discussed. A prototype space-construction system is detailed and one method by which such a system could be used to make associations is proposed. The system forms concepts that are useful to describe a set of objects, then learns how those concepts relate to each other. These relationships can then be used to construct analogies.
Extended Abstract
Bibtex
@inproceedings{
author = {Kazjon Grace, Rob Saunders, John Gero},
title = {Constructing Conceptual Spaces for Novel Associations},
editor = {Dan Ventura, Alison Pease, Rafael P ́erez y P ́erez, Graeme Ritchie and Tony Veale},
booktitle = {Proceedings of the First International Conference on Computational Creativity},
series = {ICCC2010},
year = {2010},
month = {January},
location = {Lisbon, Portugal},
pages = {120-129},
url = {http://computationalcreativity.net/iccc2010/papers/grace-saunders-gero.pdf, http://computationalcreativity.net/iccc2010/papers/grace-saunders-gero.pdf },
publisher = {International Association for Computational Creativity},
keywords = {computational, creativity},
}
Used References
1. French, R.: The computational modelling of analogy-making, Trends in Computer Science, 6: 200–205, (2002).
2. Kokinov, B.: Analogy is like cognition: dynamic, emergent and context sensitive, Advances in Analogy Research NBU Press, Sofia, (1998).
3. Hofstadter, D. and Mitchell, M.: The copycat project: a model of mental fluidity and analogy-making, in Holyoak, K. and Barnden, J. (eds), Advances in Connectionist and Neural Computation Theory, 2: 31–112, (1994).
4. Kokinov, B.: A hybrid model of reasoning by analogy, in K Holyoak and J Barnden (eds), Analogical Connections, Advances in Connectionist and Neural Computation Theory, 2: 247–318, (1994).
5. Suwa, M., Gero J. S. and Purcell, T.: Unexpected discoveries and s-inventions of design requirements: A key to creative designs, In: J. S. Gero and M. L. Maher (eds) Computational Models of Creative Design IV, University of Sydney, Australia, pp 297–320, (1999).
6. G ̈ardenfors, P.: Conceptual Spaces: The geometry of thought, MIT Press, (2000).
7. Steels, L.: Perceptually grounded meaning creation, in Proceedings of the Second International Conference on Mullti-agent Systems (ICMAS096) Los Alamitos, CA, pp 338–344, (1996).
8. Sarkar, S., Dong, A. and Gero, J. S.: Design optimization problem (re)formulation using singular value decomposition, Journal of Mechanical Design 131(8) (to ap- pear), (2009).
9. Wilson, S.W.: Classier Fitness Based on Accuracy. Evolutionary Computation, 3(2): 149–175, (1995).
Links
Full Text
http://computationalcreativity.net/iccc2010/papers/grace-saunders-gero.pdf
