Advertisement

Autoencoding Ground Motion Data for Visualisation

  • Nikolaos Gianniotis
  • Carsten Riggelsen
  • Nicolas Kühn
  • Frank Scherbaum
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7553)

Abstract

We present a new visualisation method for physical data based on the autoencoder that allows a transparent interpretation of the induced visualisation. The autoencoder is a neural network that compresses high-dimensional data into low-dimensional representations. It defines a fan-in fan-out architecture, with the middle layer composed of a small number of neurons referred to as the ‘bottleneck’. When data are propagated through the network, the bottleneck forces the autoencoder to reduce the dimensionality of the data. Physical data are manifestations of physical models that express domain knowledge. Such knowledge should be reflected in the visualisation in order to help the analyst understand why the data are projected to their particular locations. In this work we endow the standard autoencoder with this capability by extending it with extra layers. We apply our approach on a dataset of ground motions and discuss how the visualisation reflects physical aspects.

Keywords

Topographic Mapping Autoencoder Ground Motion 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Baldi, P., Hornik, K.: Neural networks and principal component analysis: Learning from examples without local minima. Neural Networks 2, 53–58 (1989)CrossRefGoogle Scholar
  2. 2.
    Bishop, C.M.: Neural networks for pattern recognition. Oxford University Press (1996)Google Scholar
  3. 3.
    Bishop, C.M., Svensén, M., Williams, C.K.I.: Magnification Factors for the GTM Algorithm. In: Gerstner, W., Hasler, M., Germond, A., Nicoud, J.-D. (eds.) ICANN 1997. LNCS, vol. 1327, pp. 64–69. Springer, Heidelberg (1997)Google Scholar
  4. 4.
    Bishop, C.M., Svensén, M., Williams, C.K.I.: GTM: The generative topographic mapping. Neural Computation 10(1), 215–234 (1998)CrossRefGoogle Scholar
  5. 5.
    Boore, D.M.: Simulation of ground motion using the stochastic method. Pure and Applied Geophysics 160, 635–676 (2003)CrossRefGoogle Scholar
  6. 6.
    Hagenbuchner, M., Sperduti, A., Tsoi, A.C.: A self-organizing map for adaptive processing of structured data. IEEE Transactions on Neural Networks 14(3), 491–505 (2003)CrossRefGoogle Scholar
  7. 7.
    Hastie, T., Tibshirani, R., Friedman, J.H.: The Elements of Statistical Learning. Springer (2001)Google Scholar
  8. 8.
    Hinton, S.: Reducing the dimensionality of data with neural networks. SCIENCE: Science 313 (2006)Google Scholar
  9. 9.
    Kohonen, T.: The self-organizing map. Proceedings of the IEEE 78(9), 1464–1480 (1990)CrossRefGoogle Scholar
  10. 10.
    Kramer, M.A.: Nonlinear principal component analysis using autoassociative neural networks. AICHE Journal 37, 233–243 (1991)CrossRefGoogle Scholar
  11. 11.
    Lawrence, N.D.: Gaussian process latent variable models for visualisation of high dimensional data. In: NIPS 16 (2004)Google Scholar
  12. 12.
    Scherbaum, F., Kuehn, N.M., Ohrnberger, M., Koehler, A.: Exploring the proximity of ground-motion models using high-dimensional visualization techniques. Earthquake Spectra 26(4), 1117–1138 (2010)CrossRefGoogle Scholar
  13. 13.
    Tan, C.C., Eswaran, C.: Autoencoder Neural Networks: A Performance Study Based on Image Reconstruction, Recognition and Compression. Lambert Academic Publishing (2009)Google Scholar
  14. 14.
    Tiňo, P., Gianniotis, N.: Metric properties of structured data visualizations through generative probabilistic modeling. In: IJCAI 2007, pp. 1083–1088 (2007)Google Scholar
  15. 15.
    Ultsch, A., Siemon, H.P.: Kohonen’s self organizing feature maps for exploratory data analysis. In: INNC Paris, vol. 90, pp. 305–308 (1990)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Nikolaos Gianniotis
    • 1
  • Carsten Riggelsen
    • 1
  • Nicolas Kühn
    • 1
  • Frank Scherbaum
    • 1
  1. 1.Institute of Earth and Environmental ScienceUniversity of PotsdamPotsdam-GolmGermany

Personalised recommendations