Skip to main content

Wagging the Dog: Human vs. Machine Inference of Causality in Visual Sequences

  • Conference paper
  • 2359 Accesses

Part of the Lecture Notes in Computer Science book series (LNAI,volume 6830)

Abstract

Causal inference among pairs of moving objects in a visual scene is compared between human observers and state-of-the-art methods in Machine Learning for causal inference. It is shown that while humans may perform intuitive and/or reasoned statistical decisions with the same overall level of accuracy as machines, they clearly exhibit biases (or priors) in their judgment and are thus able to make decisions based on much less information than is otherwise required by statistical decision algorithms. While there is no simple explanation for how humans perform this task, connectionist learning structures which implement simple time-delayed correlations (both automatic and deliberative) relying on short-term memory mechanisms may suffice to build complex bottom-up models of the physical world and the interaction therewith.

Keywords

  • Causal Inference
  • Granger Causality
  • Visual Scene
  • Visual Sequence
  • Causal Understanding

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.

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-642-22887-2_19
  • Chapter length: 10 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   64.99
Price excludes VAT (USA)
  • ISBN: 978-3-642-22887-2
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   84.99
Price excludes VAT (USA)

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Alvarez, G.A., Franconeri, S.L.: How many objects can you track? evidence for a resource-limited attentive tracking mechanism. Journal of Vision 7(13) 14, 1–10 (2007)

    Google Scholar 

  2. Billino, J., Braun, D.I., Boehm, K., Bremmer, F., Gegenfurtner, K.R.: Cortical networks for motion processing: effects of focal brain lesions on perception of different motion types. Neuropsychologia 47(10), 2133–2144 (2009)

    CrossRef  Google Scholar 

  3. Brand, M., Birnbaum, L., Cooper, P.: Sensible scenes: Visual understanding of complex structures through causal analysis (1993)

    Google Scholar 

  4. Guyon, I., Janzing, D., Schölkopf, B.: Causality: Objectives and assessment. JMLR W&CP 6, 1–38 (2010)

    Google Scholar 

  5. HÃndel, B., Thier, P., Haarmeier, T.: Visual motion perception deficits due to cerebellar lesions are paralleled by specific changes in cerebro-cortical activity. The Journal of Neuroscience: The Official Journal of the Society for Neuroscience 29(48), 15126–15133 (2009)

    Google Scholar 

  6. Makovski, T., Vázquez, G.A., Jiang, Y.V.: Visual learning in Multiple-Object tracking. PLoS ONE 3(5), e2228 (2008), http://dx.plos.org/10.1371/journal.pone.0002228

    CrossRef  Google Scholar 

  7. Neuhaus, A.H., Popescu, F.C., Grozea, C., Hahn, E., Hahn, C., Opgen-Rhein, C., Urbanek, C., Dettling, M.: Single-subject classification of schizophrenia by event-related potentials during selective attention. NeuroImage 55(2), 514–521 (2011)

    CrossRef  Google Scholar 

  8. Nolte, G., Ziehe, A., Kraemer, N., Popescu, F., Müller, K.R.: Comparison of granger causality and phase slope index. Journal of Machine Learning Research Workshop & Conference Proceedings. Causality: Objectives and Assessment, 267–276 (2010)

    Google Scholar 

  9. Nolte, G., Ziehe, A., Nikulin, V., Schlögl, A., Krämer, N., Brismar, T., Müller, K.R.: Robustly estimating the flow direction of information in complex physical systems. Physical Review Letters 00(23), 234101 (2008)

    CrossRef  Google Scholar 

  10. Pearl, J.: Causality: Models, Reasoning and Inference. Cambridge University Press, Cambridge (2000)

    MATH  Google Scholar 

  11. Pearson, A.T.: Piaget’s conception of causality. Educational Theory 22(4), 434–442 (2007)

    CrossRef  Google Scholar 

  12. Popescu, F.: Robust statistics for describing causality in multivariate time series. Journal of Machine Learning Research, Workshop and Conference Proceedings 12, 30–64 (2011)

    Google Scholar 

  13. Popescu, F., Guyon, I. (eds.): Journal of Machine Learning Research Workshop and Conference Proceedings: Causality in Time Series 12 (2011)

    Google Scholar 

  14. Pylyshyn, Z.W., Storm, R.W.: Tracking multiple independent targets: evidence for a parallel tracking mechanism. Spatial Vision 3(3), 179–197 (1988)

    CrossRef  Google Scholar 

  15. Spirtes, P., Glymour, C., Scheines, R.: Causation, Prediction, and Search, 2nd edn. MIT Press, Cambridge (2000)

    Google Scholar 

  16. Zhou, Y., Yan, S., Huang, T.S.: Pair-activity classification by bi-trajectories analysis. In: IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA, pp. 1–8 (2008)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2011 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Popescu, F. (2011). Wagging the Dog: Human vs. Machine Inference of Causality in Visual Sequences. In: Schmidhuber, J., Thórisson, K.R., Looks, M. (eds) Artificial General Intelligence. AGI 2011. Lecture Notes in Computer Science(), vol 6830. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22887-2_19

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-22887-2_19

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-22886-5

  • Online ISBN: 978-3-642-22887-2

  • eBook Packages: Computer ScienceComputer Science (R0)