THE BIRTH OF SYMBOLS IN DESIGN

In the widespread endeavour to standardize a vocabulary for design, the semantics for the terms, especially at the detailed levels, are often defined based on the exigencies of the implementation. In human usage, each symbol has a wide range of associations, and any attempt at definition will miss many of these, resulting in brittleness. Human flexibility in symbol usage is possible because our symbols are learned from a vast experience of the world. Here we propose the very first steps towards a process by which CAD systems may acquire symbols is by learning usage patterns or image schemas grounded on experience. Subsequently, more abstract symbols may be derived based on these grounded symbols, which thereby retain the flexibility inherent in a learning system. In many design tasks, the “good designs” lie along regions that can be mapped to lower dimensional surfaces or manifolds , owing to latent interdependencies between the variables. These low-dimensional structures (sometimes called chunks ) may constitute the intermediate step between the raw experience and the eventual symbol that arises after these patterns become stabilized through communication. In a multi-functional design scenario, we use a locally linear embedding (LLE) to discover these manifolds, which are compact descriptions for the space of “good designs”. We illustrate the approach with a simple 2-parameter latch-and-bolt design, and with a 8-parameter universal motor.Copyright © 2009 by ASME

[1]  John S. Gero,et al.  QUALITATIVE REPRESENTATION AND REASONING ABOUT SHAPES , 1999 .

[2]  John S. Gero,et al.  A LEARNING AND INFERENCE MECHANISM FOR DESIGN OPTIMIZATION PROBLEM (RE)- FORMULATION USING SINGULAR VALUE DECOMPOSITION , 2008 .

[3]  Robert Stone,et al.  Capturing Empirically Derived Design Knowledge for Creating Conceptual Design Configurations , 2005 .

[4]  Lucienne Blessing,et al.  Understanding the differences between how novice and experienced designers approach design tasks , 2003 .

[5]  Mark D. Gross,et al.  Design as exploring constraints , 1985 .

[6]  Shawn Martin,et al.  Estimating manifold dimension by inversion error , 2005, SAC '05.

[7]  Timothy W. Simpson,et al.  Product family design knowledge representation, aggregation, reuse, and analysis , 2007, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[8]  Simon Szykman,et al.  A functional basis for engineering design: Reconciling and evolving previous efforts , 2002 .

[9]  John S. Gero,et al.  A computational framework for concept formation for a situated design agent , 2000, Knowl. Based Syst..

[10]  Amaresh Chakrabarti,et al.  A functional representation for aiding biomimetic and artificial inspiration of new ideas , 2005, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[11]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[12]  M. Casasola,et al.  Six-month-old infants' categorization of containment spatial relations. , 2003, Child development.

[13]  Mikhail Belkin,et al.  Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering , 2001, NIPS.

[14]  J. Pine,et al.  Chunking mechanisms in human learning , 2001, Trends in Cognitive Sciences.

[15]  Ferdinand de Saussure Course in General Linguistics , 1916 .

[16]  Jean M. Mandler,et al.  A summary of The foundations of mind: Origins of conceptual thought , 2004 .

[17]  S. Vereza Philosophy in the flesh: the embodied mind and its challenge to Western thought , 2001 .

[18]  Lawrence K. Saul,et al.  Think Globally, Fit Locally: Unsupervised Learning of Low Dimensional Manifold , 2003, J. Mach. Learn. Res..

[19]  Ram D. Sriram,et al.  The Role of Knowledge in Next-generation Product Development Systems , 2001, J. Comput. Inf. Sci. Eng..

[20]  Peter J. Bickel,et al.  Maximum Likelihood Estimation of Intrinsic Dimension , 2004, NIPS.

[21]  Jonathan Cagan,et al.  Agent-Based Synthesis of Electromechanical Design Configurations , 2000 .

[22]  Ronald W. Langacker,et al.  An Introduction to Cognitive Grammar , 1986, Cogn. Sci..

[23]  Simon Szykman,et al.  Enhancing Virtual Product Representations for Advanced Design Repository Systems , 2005, J. Comput. Inf. Sci. Eng..

[24]  Jonathan Cagan,et al.  Learning from design experience in an agent-based design system , 2004 .

[25]  T. Simpson A concept exploration method for product family design , 1998 .

[26]  Ram D. Sriram,et al.  From symbol to form: a framework for conceptual design , 1996, Comput. Aided Des..

[27]  Pietro Perona,et al.  Grouping and dimensionality reduction by locally linear embedding , 2001, NIPS.

[28]  Spike Cramphorn Blink: The Power of Thinking without Thinking / Strangers to Ourselves: Discovering the Adaptive Unconscious , 2006, Journal of Advertising Research.

[29]  John R. Dixon,et al.  Guiding conceptual design through behavioral reasoning , 1994 .

[30]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[31]  J. Mandler,et al.  Understanding spatial relations: Flexible infants, lexical adults , 2003, Cognitive Psychology.

[32]  Matti Pietikäinen,et al.  Selection of the Optimal Parameter value for the Locally Linear Embedding Algorithm , 2002, FSKD.

[33]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[34]  Gabriela Goldschmidt,et al.  The Backtalk of Self-Generated Sketches , 2003, Design Issues.