Skip to main content

Combining Multiple Modes of Information Using Unsupervised Neural Classifiers

  • Conference paper
  • First Online:
Multiple Classifier Systems (MCS 2003)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 2709))

Included in the following conference series:

  • 886 Accesses

Abstract

A modular neural network-based system is presented where the component networks learn together to classify a set of complex input patterns. Each pattern comprises two vectors: a primary vector and a collateral vector. Examples of such patterns include annotated images and magnitudes with articulated numerical labels. Our modular system is trained using an unsupervised learning algorithm. One component learns to classify the patterns using the primary vectors and another classifies the same patterns using the collateral vectors. The third combiner network correlates the primary with the collateral. The primary and collateral vectors are mapped on a Kohonen self-organising feature map (SOM), with the combiner based on a variant of Hebbian networks. The classification results appear encouraging in our attempts to classify a set of scene-of-crime images and in our attempts to investigate how pre-school infants relate magnitude to articulated numerical quantities. Certain features of SOM’s, namely the topological neighbourhoods of specific nodes, allow for one to many mappings between the primary and collateral maps, hence establishing a broader association between the two vectors when compared with the association due to synchrony in a conventional Hebbian association.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Ahmad, K., Casey, M. & Bale, T. (2002). Connectionist Simulation of Quantification Skills. Connection Science, vol. 14(3), pp. 165–201.

    Article  Google Scholar 

  2. Ahmad, K., Vrusias, B. & Tariq, M. (2002). Co-operative Neural Networks and ‘Integrated’ Classification. Proceedings of the 2002 International Joint Conference on Neural Networks (IJCNN’02), vol.2, pp. 1546–1551.

    Google Scholar 

  3. Bale, T.A. (1998). Modular Connectionist Architectures and the Learning of Quantification Skills. Unpublished doctoral thesis. Guildford, UK: University of Surrey.

    Google Scholar 

  4. Dehaene, S. (1992). Varieties of Numerical Abilities. In Numerical Cognition (1993), pp.1–42. Cambridge, MA.: Blackwell Publishers.

    Google Scholar 

  5. Haralick, R.M., Shanmugam, K. & Dinstein, I. (1973). Textural Features for Image Classification. IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-3(6), pp.610–621.

    Article  Google Scholar 

  6. Hebb, D.O. (1949). The Organization of Behavior: A Neuropsychological Theory. New York: John Wiley & Sons.

    Google Scholar 

  7. Jacobs, R.A., Jordan, M.I., & Barto, A.G. (1991). Task Decomposition through Competition in a Modular Connectionist Architecture: The What and Where Vision Tasks. Cognitive Science, vol. 15, pp. 219–250.

    Article  Google Scholar 

  8. Jing, X., & Zhang, D. (2003) Face recognition based on linear classifiers combination. Neurocomputing, vol. 50, pp. 485–488.

    Article  MATH  Google Scholar 

  9. Kaufman, E.L., Lord, M.W., Reese, T.W. & Volkmann, J. (1949). The Discrimination of Visual Number. American Journal of Psychology, vol. 62, pp. 498–525.

    Article  Google Scholar 

  10. Kittler, J., Hatef, M. Duin, R.P.W. & Matas, J. (1998). On Combining Classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20(3), pp. 226–239.

    Article  Google Scholar 

  11. Kohonen, T. (1997). Self-Organizing Maps, 2nd Ed. Berlin, Heidelberg, New York: Springer-Verlag.

    MATH  Google Scholar 

  12. Lawrence, S., Giles, C.L., Ah Chung Tsoi & Back, A.D. (1997). Face Recognition: A Convolutional Neural Network Approach. IEEE Transactions on Neural Networks, vol. 8(1) pp 98–113.

    Article  Google Scholar 

  13. McCloskey, M. (1992). Cognitive Mechanisms in Number Processing and Calculation: Evidence from Dyscalculia. In Dehaene, S. (Ed), Numerical Cognition (1993), pp. 107–157. Cambridge, MA.: Blackwell Publishers.

    Google Scholar 

  14. McCloskey, M., Caramazza, A. & Basili, A. (1985). Cognitive Mechanisms in Number Processing and Calculation: Evidence from Dyscalculia. Brain and Cognition, vol. 4, pp. 171–196.

    Article  Google Scholar 

  15. Schettini, R., Brambilla, C. & Cusano, C. (2002). Content-based Classification of Digital Photos. In Roli, F. & Kittler, J. (Eds), Proceedings of the Third International Workshop on Multiple Classifier Systems (MCS 2002), LNCS 2364, pp. 272–282.

    Google Scholar 

  16. Sharkey, A.J.C. (1999). Multi-net Systems. In Sharkey, A.J.C. (Ed), Combining Artificial Neural Nets: Ensemble and Modular Multi-Net Systems, pp.1–30. Berlin, Heidelberg, New York: Springer-Verlag.

    Google Scholar 

  17. Sharkey, A.J.C. (2002). Types of Multinet System. In Roli, F. & Kittler, J. (Eds), Proceedings of the Third International Workshop on Multiple Classifier Systems (MCS 2002), LNCS 2364, pp. 108–117.

    Google Scholar 

  18. Sinclair, J. M. (Ed.) (1993) Collins English Dictionary and Thesaurus. Harper Collins.

    Google Scholar 

  19. Srihari R.K., (1995). Use of Collateral Text in Understanding Photos, Artificial Intelligence Review, special issue on Integrating Language and Vision, Volume 8, pp. 409–430.

    Google Scholar 

  20. Willshaw, D.J. & von der Malsburg, C. (1976). How Patterned Neural Connections can be set up by Self-Organization. Proceedings of the Royal Society, Series B, vol. 194, pp. 431–445.

    Google Scholar 

  21. Zhou, X.S., Rui Y. & Huang S.T. (1999). Water-filling: A Novel Way for Image Structural Feature Extraction. Proceedings of the IEEE International Conference on Image Processing, pp. 570–574.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2003 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Ahmad, K., Casey, M., Vrusias, B., Saragiotis, P. (2003). Combining Multiple Modes of Information Using Unsupervised Neural Classifiers. In: Windeatt, T., Roli, F. (eds) Multiple Classifier Systems. MCS 2003. Lecture Notes in Computer Science, vol 2709. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44938-8_24

Download citation

  • DOI: https://doi.org/10.1007/3-540-44938-8_24

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-40369-2

  • Online ISBN: 978-3-540-44938-6

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics