Hostname: page-component-78c5997874-ndw9j Total loading time: 0 Render date: 2024-11-11T00:07:22.957Z Has data issue: false hasContentIssue false
  • English
  • Français

Learning while designing

Published online by Cambridge University Press:  07 June 2005

GOURABMOY NATH  and
JOHN S. GERO
GOURABMOY NATH
Affiliation:
Technology LABS, Amadeus S.A.S., 485 Route Du Pin Montard, Les Bouillides BP 69, 06902 Sophia Antipolis Cedex, France
JOHN S. GERO
Affiliation:
Key Centre of Design Computing and Cognition, University of Sydney, Sydney, NSW 2006, Australia
Get access Rights & Permissions [Opens in a new window]

Abstract

This paper describes how a computational system for designing can learn useful, reusable, generalized search strategy rules from its own experience of designing. It can then apply this experience to transform the design process from search based (knowledge lean) to knowledge based (knowledge rich). The domain of application is the design of spatial layouts for architectural design. The processes of designing and learning are tightly coupled.

Keywords

Design ProcessLearningSituationsStrategy Rules
Type
Research Article
Information
AI EDAM , Volume 18 , Issue 4 , November 2004 , pp. 315 - 341
Copyright
© 2004 Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

REFERENCES

Braudaway, W. & Tong, C. (1989). Automated synthesis of constrained generators. Proc. 11th Int. Joint Conf. Artificial Intelligence, pp. 583–589. Menlo Park, CA: AAAI Press.
Brown, D.C. (1996). Knowledge compilation in routine design problem solving systems: Research abstract. Artificial Intelligence for Engineering Design, Analysis and Manufacturing 10(2), 137–138.Google Scholar
Brown, D.C. & Spillane, M. (1991). An experimental evaluation of some design knowledge compilation mechanisms. In Artificial Intelligence in Design'91 (Gero, J.S., Ed.), pp. 323–325. Oxford: Butterworth Heinemann.
Cagan, J. & Mitchell, W.J. (1993). Optimally directed shape generation by shape annealing. Environment and Planning B: Planning and Design 20, 5–12.Google Scholar
Carbonell, J.G., Knoblock, C.A., & Minton, S. (1991). PRODIGY: an integrated architecture for Prodigy. In Architectures for Intelligence (VanLehn, K., Ed.), pp. 241–278. Hillsdale, NJ: Erlbaum.
Chabot, R. & Brown, D.C. (1994). Knowledge compilation using constraint inheritance. Artificial Intelligence for Engineering Design, Analysis and Manufacturing 8(2), 125–142.Google Scholar
Doorenbos, B. (1993). Matching 100,000 learned rules. Proc. 11th National Conf. Artificial Intelligence, pp. 290–296.
Doorenbos, B., Tambe, M., & Newell, A. (1992). Learning 10,000 chunks: what's it like out there? Proc. 10th National Conf. Artificial Intelligence, pp. 830–836.
Forgy, C. (1982). Rete: a fast algorithm for the many pattern/many object pattern match problem. Artificial Intelligence 19, 17–37.Google Scholar
Gero, J.S. (1998). Towards a model of designing which includes its situatedness. In Universal Design Theory (Grabowski, H., Rude, S. & Grein, G., Eds.), pp. 47–56. Aachen, Germany: Shaker Verlag.
Kim, J. & Rosenbloom, P. (1996). Learning efficient rules by maintaining the explanation structure. Proc. 13th National Conf. Artificial Intelligence, pp. 763–770.
Laird, J., Newell, A., & Rosenbloom, P. (1986). Chunking in SOAR: the anatomy of a general learning mechanism. Machine Learning 1, 11–46.Google Scholar
Laird, J., Newell, A., & Rosenbloom, P. (1987). SOAR: An architecture for general intelligence. Artificial Intelligence 33, 1–64.Google Scholar
Liu, J. & Brown, D.C. (1991). Generating design decomposition knowledge for parametric design problems. In Artificial Intelligence in Design'91 (Gero, J.S., Ed.), pp. 661–678. Dordrecht: Kluwer.
Manfaat, D., Duffy, A.H.B., & Lee, B.S. (1996). Generalization of spatial layouts. Workshop on Machine Learning in Design, Artificial Intelligence in Design'96. Stanford, CA: Stanford University.
Minton, S. (1988). Quantitative results concerning the utility of explanation-based learning. Proc. Seventh National Conf. Artificial Intelligence, pp. 564–569.
Modi, A., Newell, A., Steier, D., & Westerberg, A. (1995a). Building a chemical process design system with SOAR—1: design issues. Computers and Chemical Engineering 19(1), 75–89.Google Scholar
Modi, A., Newell, A., Steier, D., & Westerberg, A. (1995b). Building a chemical engineering process design system with SOAR—2: learning issues. Computers and Chemical Engineering 19(3), 345–361.Google Scholar
Mostow, J. (1990). Towards automated development of specialized algorithms for design synthesis: knowledge compilation as an approach to computer aided design. Research in Engineering Design 1, 167–186.Google Scholar
Nath, G. (2000). A model of situation learning in design. PhD Thesis. Sydney, Australia: University of Sydney, Department of Architectural and Design Science.
Nath, G. (2003). A computer program automatically acquiring some skills for a simple design problem. In Expertise in Design (Cross, N. & Edmonds, E., Eds.), pp. 323–329. Sydney, Australia: Creativity and Cognition Studios Press.
Newell, A. (1990). Unified Theories of Cognition. Cambridge, MA: Harvard University Press.
Rosenbloom, P. & Laird, J. (1986). Mapping explanation-based generalization onto SOAR. Proc. Fifth National Conf. Artificial Intelligence, pp. 561–567. Los Altos, CA: AAAI Press.
Reddy, G. & Cagan, J. (1995). An improved shape annealing algorithm for truss topology generation. ASME Journal of Mechanical Design 117(2), 315–321.Google Scholar
Rosenman, M. (1996). The generation of form using an evolutionary approach. In Artificial Intelligence in Design'96 (Gero, J.S. & Sudweeks, F., Eds.), pp. 643–662. Dordrecht: Kluwer Academic.
Schmidt, L.C. & Cagan, J. (1998). Optimal configuration design: an integrated approach using grammars. ASME Journal of Mechanical Design 120(1), 2–9.Google Scholar
Samuel, A.L. (1959). Some studies in machine learning using the game of checkers. IBM Journal of Research and Development 3, 210–229.Google Scholar
Shea, K. & Cagan, J. (1997). Innovative dome design: applying geodesic patterns with shape annealing. Artificial Intelligence for Engineering Design, Analysis and Manufacturing 11, 379–394.Google Scholar
Sloan, W. & Brown, D.C. (1988). Adjusting constraints in routine design knowledge. Workshop on AI in Design: Proc. Seventh National Conf. Artificial Intelligence. Menlo Park, CA: AAAI Press.
Tambe, M. (1991). Eliminating conbinatorics from production match. PhD Thesis, Carnegie Mellon University.
Tambe, M. & Newell, A. (1988). Some chunks are expensive. In Proc. Fifth Int. Conf. Machine Learning (Laird, J.E., Ed.), pp. 451–458. San Mateo, CA: Morgan Kaufmann.
Tambe, M. & Rosenbloom, P.S. (1989). Eliminating expensive chunks by restricting expressiveness. Proc. 11th Int. Joint Conf. Artificial Intelligence, pp. 731–737.
Vale, C.A.W. & Shea, K. (2003a). A machine learning-based approach to accelerating computational design synthesis. Proc. 14th Int. Conf. Engineering Design (ICED 03), Stockholm.
Vale, C.A.W. & Shea, K. (2003b). Learning intelligent modification strategies in design synthesis. Proc. AAAI Spring Symp. Computational Synthesis, pp. 247–254. Palo Alto, CA.
Voigt, K. & Tong, C. (1989). Automating the construction of patchers that satisfy global constraints. Proc. 11th Int. Joint Conf. Artificial Intelligence, pp. 1446–1452. Menlo Park, CA: AAAI Press.