Skip to main content

A Model of Category Learning with Attention Augmented Simplistic Prototype Representation

  • Conference paper
Advances in Neural Networks - ISNN 2006 (ISNN 2006)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 3971))

Included in the following conference series:

  • 106 Accesses

Abstract

Cognitive models has been a main tool for quantitatively testing theories on human cognition. The results of previous cognitive modeling research collectively suggest the comparative advantage of exemplar over prototype accounts in human cognition. However, we hypothesized that unsuccessful outcomes by traditional prototype models may be the unforeseen consequences of the algorithmic constraints imposed on the models, but not of the implausibility of the theory itself. To test this hypothesis, a new cognitive model based on prototype theory with a more complex and realistic attention system is introduced and evaluated in the present study. A simulation study shows that a new model termed CASPRE resulted in a substantial improvement as compared with the traditional prototype model in replicating empirical findings and that it performed marginally better than an exemplar model, thus confirming our hypothesis.

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

Access this chapter

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. Medin, D.L., Schaffer, M.M.: Context Theory of Classification Learning. Psychological Review 85, 207–238 (1978)

    Article  Google Scholar 

  2. Nosofsky, R.M.: Attention, Similarity and the Identification-Categorization Relationship. Journal of Experimental Psychology: General 115, 39–57 (1986)

    Article  Google Scholar 

  3. Matsuka, T.: Generalized Exploratory Model of Human Category Learning. International Journal of Computational Intelligence 1, 7–15 (2004)

    Google Scholar 

  4. Aha, D.W., Goldstone, R.L.: Concept Learning and Flexible Weighting. In: Proceedings of the 14h Annual Meeting of the Cognitive Science Society, pp. 534–539. Lawrence Erlbaum Associates, Hillsdale (1992)

    Google Scholar 

  5. Anderson, J.R., Fincham, J.M.: Categorization and Sensitivity to Correlation. Journal of Experimental Psychology: Learning, Memory & Cognition 22, 119–128 (1996)

    Article  Google Scholar 

  6. Matsuka, T.: Simple, Individually Unique, and Context-Dependent Learning Method for Models of Human Category Learning. Behavior Research Methods 37, 240–255 (2005)

    Article  Google Scholar 

  7. Matsuka, T.: Modeling Human Learning as Context Dependent Knowledge Utility Optimization. In: Wang, L., Chen, K., S. Ong, Y. (eds.) ICNC 2005. LNCS, vol. 3610, pp. 933–946. Springer, Heidelberg (2005)

    Chapter  Google Scholar 

  8. Kohonen, T.: Self-Organizing Maps, 3rd edn. Springer, Berlin (2001)

    MATH  Google Scholar 

  9. Love, B.C., Medin, D.L., Gureckis, T.M.: SUSTAIN: A Network Model of Category Learning. Psychological Review 111, 309–332 (2004)

    Article  Google Scholar 

  10. Kruschke, J.E.: ALCOVE: An Exemplar-Based Connectionist Model of Category Learning. Psychological Review 99, 22–44 (1992)

    Article  Google Scholar 

  11. Smith, J.D., Minda, J.P.: Thirty Categorization Results in Search of a Model. Journal of Experimental Psychology: Learning, Memory, and Cognition 26, 3–27 (2000)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2006 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Matsuka, T. (2006). A Model of Category Learning with Attention Augmented Simplistic Prototype Representation. In: Wang, J., Yi, Z., Zurada, J.M., Lu, BL., Yin, H. (eds) Advances in Neural Networks - ISNN 2006. ISNN 2006. Lecture Notes in Computer Science, vol 3971. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11759966_6

Download citation

  • DOI: https://doi.org/10.1007/11759966_6

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-34439-1

  • Online ISBN: 978-3-540-34440-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics