Title: Discovery of symbols in design

Authors: Madan Mohan Dabbeeru

Addresses: Indian Institute of Technology Kanpur, Uttarpradesh, 208 016, India

Abstract: In this work, we propose a mechanism for learning grounded symbols based on design experience as acquired by a CAD system. We discover the functionally feasible regions (FFRs) lying along lower dimensional surfaces or manifolds, reflecting latent interdependencies between design variables (sometimes called chunks) constitute the intermediate step between raw experience and the eventual symbol that arises after these patterns become stabilised through communication. We search this lower-dimensional manifolds using either linear or nonlinear techniques, and demonstrate low-dimensionality at three stages of an 'infant designer': a) learning image schemas for fits and clearances using linear algorithms; b) universal motor, 2-parameter - learning a non-linear manifold; c) universal motor, 8-parameter, reducing to two parameters or chunks using both linear and nonlinear mappings.

Keywords: image schema; cognitive architecture; expertise; design semantics; grounded symbol acquisition; infant designers; nonlinear manifold learning; principal component analysis; PCA; symbol discovery; CAD; design variables; grounded symbols.

DOI: 10.1504/IJIEI.2015.069086

International Journal of Intelligent Engineering Informatics, 2015 Vol.3 No.1, pp.1 - 22

Received: 30 Nov 2013
Accepted: 24 Oct 2014
Published online: 27 Apr 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article