Associative Spatial Networks in Architectural Design: Artificial Cognition of Space Using Neural Networks with Spectral Graph Theory

  • John Harding
  • Christian Derix
Conference paper

Abstract

This paper looks at a new way of incorporating unsupervised neural networks in the design of an architectural system. The approach involves looking the whole lifecycle of a building and its coupling with its environment. It is argued that techniques such as dimensionality reduction are well suited to architectural design problems whereby complex problems are commonplace. An example project is explored, that of a reconfigurable 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 dynamic spatial arrangements whose nature are not known a priori. By utilising the machine in combination with user feedback, a coupling between the building system and the users of the space is achieved throughout the whole system life cycle.

Keywords

Plan Graph Architectural Design Laplacian Spectrum Graph Spectrum System Life Cycle 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bauer, H.U., Villmann, T.H.: Growing a Hypercubical Output Space in a Self-Organizing Feature Map. International Computer Science Institute, Berkeley (1995)Google Scholar
  2. 2.
    Derix, C., Thum, R.: Artificial Neural Network Spaces. In: International Conference on Generative Art, MilanGoogle Scholar
  3. 3.
    Ireland, T., Derix, C.: An analysis of the Poly-dimensionality of living - An experiment in the application of 3-dimensional self-organising maps to evolve form. In: 21st eCAADe Conference Proceedings, Graz, September 2003, pp. 449–456 (2003)Google Scholar
  4. 4.
    Derix, C.: Approximating Phenomenological Space. In: Proceedings of Intelligent Computing in Engineering and Architecture, Ascona, Switzerland, pp. 136–146. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  5. 5.
    Derix, C.: Genetically Modified Spaces. In: Littlefield, D. (ed.) Space Craft - Developments In Architectural Computing, pp. 22–26. RIBA Publishing (2008)Google Scholar
  6. 6.
    Eppstein, D., Paterson, M.S., Yao, F.: On nearest-neighbor graphs. Discrete and Computational Geometry 17(3), 263–282 (1997)MathSciNetMATHCrossRefGoogle Scholar
  7. 7.
    Frazer, J.H.: An Evolutionary Architecture. Architectural Association, London (1995)Google Scholar
  8. 8.
    Frazer, J.H.: The cybernetics of architecture: A tribute to the contribution of Gordon Pask. Kybernetes 30(5), 641–651 (2001)MATHCrossRefGoogle Scholar
  9. 9.
    Fritzke, B.: Growing cell structures, a self-orgainising network for unsupervised and supervised learning. International Computer Science Institute, Berkeley (1993)Google Scholar
  10. 10.
    Fritzke, B.: Kohonen feature maps and growing cell structures, a performance comparison. In: Advances in Neural Information Processing Systems (1993)Google Scholar
  11. 11.
    Fritzke, B.: A growing neural gas network learns topologies. NIPS, Denver (1994)Google Scholar
  12. 12.
    Fritzke, B.: A Self-Organizing Network that can follow Non-Stationary Distributions. In: International Conference on Artificial Neural Networks, pp. 613–618. Springer, Heidelberg (1997)Google Scholar
  13. 13.
    Hanna, S.: Representing Style by Feature Space Archetypes: Description and Emulation of Spatial Styles in an Architectural Context. In: Gero, J.S. (ed.) Design Computing and Cognition 2006, pp. 3–22. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  14. 14.
    Hanna, S.: Automated Representation of Style by Feature Space Archetypes: Distinguishing Spatial Styles from Generative Rules. International Journal of Architectural Computing 1(5), 1–23 (2007)Google Scholar
  15. 15.
    Hillier, B., Hanson, J.: The Social Logic of Space. New edition. Cambridge University Press, Cambridge (1989)Google Scholar
  16. 16.
    Jupp, J., Gero, J.S.: Towards computational analysis of style in architectural design. In: Argamon, S. (ed.) IJCAI 2003 Workshop on Computational Approaches to Style Analysis and Synthesis, IJCAI, Acapulco, pp. 1–10 (2003)Google Scholar
  17. 17.
    Kalay, Y.: Architecture’s New Media: Principles, Theories, and Methods of Computer-Aided Design. MIT Press, Cambridge (2004)Google Scholar
  18. 18.
    Kohonen, T.: Self-organizing maps, 3rd edn. Springer, Berlin (2000)Google Scholar
  19. 19.
    Langley, P., Derix, C., Coates, P.: Meta-Cognitive Mappings: Growing Neural Networks for Generative Urbanism. In: Generative Arts conference, Milan (2007)Google Scholar
  20. 20.
    Martinetz, T.M., Schulten, K.J.: A neural-gas network learns topologies. In: Kohonen, T., et al. (eds.) Artificial Neural Networks, pp. 397–402 (1991)Google Scholar
  21. 21.
    Maturana, H.R.: Biology of Language: The Epistemology of Reality. In: Miller, G.A., Lenneberg, E. (eds.) Psychology and Biology of Language and Thought: Essays in Honor of Eric Lenneberg, pp. 27–63. Academic Press, New York (1978)Google Scholar
  22. 22.
    Pask, G.: A Comment, a Case History and a Plan. in Cybernetic Serendipity. In: Reichardt, J., Rapp, C. (eds.) Reprinted in Cybernetics, Art and Ideas, pp. 76–99. Studio Vista, London (1971)Google Scholar
  23. 23.
    Petrovic, I., Svetel, I.: From Number Cruncher to Digital Being: The Changing Role of Computer in CAAD. In: Architectural Computing from Turing to 2000, eCAADe Conference Proceedings Liverpool, vol. 15(17), pp. 33–39 (1999)Google Scholar
  24. 24.
    Steadman, P.: Architectural Morphology: An Introduction to the Geometry of Building Plans, Pion, London (1983)Google Scholar
  25. 25.
    Zhu, P., Wilson, R.C.: A study of graph spectra for comparing graphs and trees. Pattern Recognition, Pergamon 41(9), 2833–2841 (2008)MATHCrossRefGoogle Scholar

Copyright information

© Springer Netherlands 2011

Authors and Affiliations

  • John Harding
    • 1
  • Christian Derix
    • 2
  1. 1.RambollUniversity of BathUK
  2. 2.Aedas R&DUniversity of East LondonUK

Personalised recommendations