CumInCAD is a Cumulative Index about publications in Computer Aided Architectural Design
supported by the sibling associations ACADIA, CAADRIA, eCAADe, SIGraDi, ASCAAD and CAAD futures

id 1fce
authors Harding J, Derix C
year 2010
title Associative Spatial Networks in Architectural Design - Artificial Cognition of Space using Neural Networks with Spectral Graph Theory
source Design Computation Cognition conference 2010
summary This paper looks at a new way of employing unsupervised neural networks in the design of an architectural system. The method described involves looking the whole lifecycle of a building and its coupling with its environment. Techniques such as dimensionality reduction, it is argued, are well suited to architectural design whereby complex problems are commonplace. An example project is explored - that of an exhibition space where multiple ephemeral exhibitions are housed at any given time. A modified growing neural gas algorithm is employed in order cognize similarities of spaces whose nature are not known a priori. By utilising the machine, a coupling between the building system and the users of the space is explored throughout the whole project life of the design.
keywords space planning, architectural design, neural networks, cognition
series other
type normal paper
email christian.derix@aedas.com
more http://www.springer.com/engineering/mechanical+engineering/book/978-94-007-0509-8
references Content-type: text/plain
last changed 2012/09/17 19:34
HOMELOGIN (you are user _anon_353317 from group guest) Works Powered by SciX Open Publishing Services 1.002