Journal article
Learning symbolic formulations in design: Syntax, semantics, and knowledge reification
AI EDAM, v 24(1), pp 63-85
01 Feb 2010
Abstract
An artificial intelligence (AI) algorithm to automate symbolic design reformulation is in enduring challenge in design automation. Existing research shows that design tools either require high levels of knowledge engineering or large databases of training cases. To address these limitations, we present a singular value decomposition (SVD) and unsupervised cluster-based method that performs design reformulation by acquiring semantic knowledge from the syntax of design representations. The development of the method was analogically inspired by applications of SVD in statistical natural language processing and digital image Processing. We demonstrate our method on an analytically formulated hydraulic cylinder design problem and an aeroengine design problem formulated using a nonanalytic design structure matrix form. Our results show that the method automates various design reformulation tasks oil problems of varying sizes from different design domains, stated ill analytic and nonanalytic representational forms. The behavior of the method presents observations that cannot be explained by pure symbolic AI approaches, including uncovering patterns of implicit knowledge that are not readily encoded as logical rules. and automating tasks that require the associative transformation of sets of inputs to experiences. As in explanation, We relate the structure and performance of our algorithm with findings in cognitive neuroscience, and present a set of theoretical postulates addressing an alternate perspective oil how symbols may interact with each other in experiences to reify semantic knowledge in design representations.
Metrics
1 Record Views
Details
- Title
- Learning symbolic formulations in design: Syntax, semantics, and knowledge reification
- Creators
- Somwrita Sarkar - The University of SydneyAndy Dong - The University of SydneyJohn S. Gero - George Mason University
- Publication Details
- AI EDAM, v 24(1), pp 63-85
- Publisher
- Cambridge Univ Press
- Number of pages
- 23
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Psychological and Brain Sciences (Psychology)
- Web of Science ID
- WOS:000274375100006
- Scopus ID
- 2-s2.0-77952397326
- Other Identifier
- 991022157482104721