Learning Symbolic Formulations in Design Optimization
This paper presents a learning and inference mechanism for unsupervised learning of semantic concepts from purely syntactical examples of design optimization formulation data. Symbolic design formulation is a tough problem from computational and cognitive perspectives, requiring domain and mathematical expertise. By conceptualizing the learning problem as a statistical pattern extraction problem, the algorithm uses previous design experiences to learn design concepts. It then extracts this learnt knowledge for use with new problems. The algorithm is knowledge-lean, needing only the mathematical syntax of the problem as input, and generalizes quickly over a very small training data set. We demonstrate and evaluate the method on a class of hydraulic cylinder design problems.
Unable to display preview. Download preview PDF.
- 1.Papalambros PY, Wilde DJ (2000) Principles of optimal design. Cambridge University PressGoogle Scholar
- 5.Moss J, Cagan J, Kotovsky K (2004) Learning from design experience in an agent-based system. Research in Engineering Design 15: 77–92Google Scholar
- 6.Strang G (2003) Introduction to linear algebra. Wellesley-Cambridge PressGoogle Scholar
- 12.Campbell MI, Cagan J, Kotovsky K (2003) The A-design approach to managing automated design synthesis. Research in Engineering Design 14: 12–24Google Scholar
- 15.Hill A, Song S, Dong A, Agogino A (2001) Identifying shared understanding in design teams using document analysis. 13th International Conference on Design Theory and Methodology, DETC2001/ DTM-21713, ASME Press, Chicago, ILGoogle Scholar
- 16.Moss J, Kotovsky K, Cagan J (2004) Cognitive investigations into knowledge representation in engineering design. In JS Gero (ed), Design Computing and Cognition '04, Kluwer: 97–116Google Scholar