Skip to main content

Selective Attention Improves Learning

  • Conference paper

Part of the Lecture Notes in Computer Science book series (LNTCS,volume 5769)

Abstract

We demonstrate that selective attention can improve learning. Considerably fewer samples are needed to learn a source separation problem when the inputs are pre-segmented by the proposed model. The model combines biased-competition model for attention with a habituation mechanism which allows the focus of attention to switch from one object to another. The criteria for segmenting objects are estimated from data and are shown to generalise to new objects.

Keywords

  • Selective attention
  • perceptual learning
  • segmentation

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

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-642-04277-5_29
  • 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   169.00
Price excludes VAT (USA)
  • ISBN: 978-3-642-04277-5
  • 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   219.99
Price excludes VAT (USA)

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Ahissar, M., Hochstein, S.: Attentional control of early perceptual learning. Proceedings of the National Academy of Sciences 90, 5718–5722 (1993)

    CrossRef  Google Scholar 

  2. Reynolds, J.H., Chelazzi, L.: Attentional modulation of visual processing. Annual Review of Neuroscience 27, 611–647 (2004)

    CrossRef  Google Scholar 

  3. Miltner, W.H.R., Braun, C., Arnold, M., Witte, H., Taub, E.: Coherence of gamma-band EEG activity as a basis for associative learning. Nature 397(6718), 434–436 (1999)

    CrossRef  Google Scholar 

  4. Särelä, J., Valpola, H.: Denoising source separation: a novel approach to ICA and feature extraction using denoising and Hebbian learning. In: Correlation Learning Workshop in the Eighteenth Canadian Conference on Artificial Intelligence, Victoria, Canada, May 2005, pp. 45–56 (2005)

    Google Scholar 

  5. Todorovic, D.: Gestalt principles. Scholarpedia 3(12), 5345 (2008)

    CrossRef  Google Scholar 

  6. Desimone, R., Duncan, J.: Neural mechanisms of selective visual attention. Annual Review of Neuroscience 18, 193–222 (1995)

    CrossRef  Google Scholar 

  7. Usher, M., Niebur, E.: Modeling the temporal dynamics of it neurons in visual search: A mechanism for top-down selective attention. Journal of cognitive neuroscience 8, 311–327 (1996)

    CrossRef  Google Scholar 

  8. Deco, G., Rolls, E.T.: A neurodynamical cortical model of visual attention and invariant object recognition. Vision research 44, 621–642 (2004)

    CrossRef  Google Scholar 

  9. Itti, L., Koch, C.: A saliency-based search mechanism for overt and covert shifts of visual attention. Vision Research 40, 1489–1506 (2000)

    CrossRef  Google Scholar 

  10. Wang, D.L., Terman, D.: Locally excitatory globally inhibitory oscillator networks. IEEE Trans. Neural Net. 6, 283–286 (1995)

    CrossRef  Google Scholar 

  11. Choe, Y., Miikkulainen, R.: Self-organization and segmentation in a laterally connected orientation map of spiking neurons. Neurocomputing 21(1-3), 139–158 (1998)

    CrossRef  MATH  Google Scholar 

  12. Weng, S., Wersing, H., Steil, J., Ritter, H.: Learning lateral interactions for feature binding and sensory segmentation from prototypic basis functions. IEEE Transactions Neural Networks 17(4), 843–862 (2006)

    CrossRef  Google Scholar 

  13. Lessmann, M., Würtz, R.P.: Image segmentation by a network of cortical macrocolumns with learned connection weights. In: Proceedings of Biologically Inspired Cooperative Computing (BICC). Springer, Heidelberg (2008)

    Google Scholar 

  14. Walther, D., Rutishauser, U., Koch, C., Perona, P.: Selective visual attention enables learning and recognition of multiple objects in cluttered scenes. Computer Vision and Image Understanding 100, 41–63 (2005)

    CrossRef  Google Scholar 

  15. Kruschke, J.K.: Toward a unified model of attention in associative learning. Journal of Mathematical Psychology 45, 812–863 (2001)

    CrossRef  MathSciNet  MATH  Google Scholar 

  16. FastICA: The FastICA MATLAB package (1998), http://www.cis.hut.fi/projects/ica/fastica/

  17. Hyvärinen, A., Karhunen, J., Oja, E.: Independent component analysis. Wiley, Chichester (2001)

    CrossRef  Google Scholar 

  18. Yli-Krekola, A.: A bio-inspired computational model of covert attention and learning. Master’s thesis, Helsinki University of Technology, Finland (2007)

    Google Scholar 

  19. Amari, S., Cichocki, A., Yang, H.H.: A new learning algorithm for blind source separation. In: Advances in Neural Information Processing 8 (Proc. NIPS 1995), pp. 757–763. MIT Press, Cambridge (1996)

    Google Scholar 

  20. Ackley, D.H., Hinton, G.E., Sejnowski, T.J.: A learning algorithm for boltzmann machines. Cognitive Science 9(1), 147–169 (1985)

    CrossRef  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2009 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Yli-Krekola, A., Särelä, J., Valpola, H. (2009). Selective Attention Improves Learning. In: Alippi, C., Polycarpou, M., Panayiotou, C., Ellinas, G. (eds) Artificial Neural Networks – ICANN 2009. ICANN 2009. Lecture Notes in Computer Science, vol 5769. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04277-5_29

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-04277-5_29

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-04276-8

  • Online ISBN: 978-3-642-04277-5

  • eBook Packages: Computer ScienceComputer Science (R0)