Advertisement

A Computationally and Cognitively Plausible Model of Supervised and Unsupervised Learning

  • David M. W. Powers
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7888)

Abstract

Both empirical and mathematical demonstrations of the importance of chance-corrected measures are discussed, and a new model of learning is proposed based on empirical psychological results on association learning. Two forms of this model are developed, the Informatron as a chance-corrected Perceptron, and AdaBook as a chance-corrected AdaBoost procedure. Computational results presented show chance correction facilitates learning.

Keywords

Chance-corrected evaluation Kappa Perceptron AdaBoost 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ward, W.C., Jenkins, H.M.: The display of information and the judgement of contingency. Canadian Journal of Psychology 19, 231–241 (1965)CrossRefGoogle Scholar
  2. 2.
    Shanks, D.R.: The psychology of association learning. CUP, Cambridge (1995)CrossRefGoogle Scholar
  3. 3.
    Perruchet, P., Peereman, R.: The exploitation of distributional information in syllable processing. J. Neurolinguistics 17, 97−119 (2004)Google Scholar
  4. 4.
    Cohen, J.: A coefficient of agreement for nominal scales. Educational and Psychological Measurement, 37–46 (1960)Google Scholar
  5. 5.
    Fleiss, J.L.:  Statistical methods for rates and proportions, 2nd edn. Wiley, Chichester (1981)zbMATHGoogle Scholar
  6. 6.
    Entwisle, J., Powers, D.M.W.: The Present Use of Statistics in the Evaluation of NLP Parsers. In: NeMLaP3/CoNLL98 Joint Conference, pp. 215–224. ACL (1998)Google Scholar
  7. 7.
    Flach, P.A.: The Geometry of ROC Space: Understanding Machine Learning Metrics through ROC Isometrics. In: Proceedings of the Twentieth International Conference on Machine Learning (ICML 2003), pp. 226–233 (2003)Google Scholar
  8. 8.
    Powers, D.M.W.: Recall and Precision versus the Bookmaker. In: International Conference on Cognitive Science, pp. 529–534 (2003)Google Scholar
  9. 9.
    Powers, D.M.W.: The Problem of Kappa. In: 13th Conference of the European Chapter of the Association for Computational Linguistics, pp. 345–355 (2012)Google Scholar
  10. 10.
    Powers, D.M.W.: Neurolinguistics and Psycho-linguistics as a Basis for Computer Acquisition of Natural Language. SIGART 84, 29–34 (1983)CrossRefGoogle Scholar
  11. 11.
    Powers, D.M.W.: Goals, Issues and Directions in Machine Learning of Natural Language and Ontology. SIGART Bulletin 2(1), 101–114 (1991)Google Scholar
  12. 12.
    Finch, S.P.:  Finding Structure in Language. Ph.D. thesis, University of Edinburgh (1993)Google Scholar
  13. 13.
    Powers, D.M.W.: Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness & Correlation. Journal of Machine Learning Technologies 2(1), 37–63 (2011)MathSciNetGoogle Scholar
  14. 14.
    Collobert, R., Bengio, S.:  Links between Perceptrons, MLPs and SVMs. IDIAP Research Report, Dalle Molle Institute for Perceptual Artificial Intelligence (2004)Google Scholar
  15. 15.
    Elman, J.L.: Finding structure in time. Cognitive Science 14, 179–211 (1990)CrossRefGoogle Scholar
  16. 16.
    Elman, J.L., Bates, E.A., Johnson, M.H., Karmiloff-Smith, A., Parisi, D., Plukett, K.: Rethinking innateness: A connectionist perspective on development. MIT Press, Cambridge (1996)Google Scholar
  17. 17.
    Munakata, Y., Pfaffly, J.: Hebbian learning and development. Developmental Science 7(2), 141–148 (2004)CrossRefGoogle Scholar
  18. 18.
    Powers, D.M.W., Turk, C.C.R.: Machine Learning of Natural Language. Springer, Berlin (1989)zbMATHCrossRefGoogle Scholar
  19. 19.
    Hebb, D.O.: The organization of behaviour. Wiley, New York (1949)Google Scholar
  20. 20.
    Littlestone, N.: Learning Quickly When Irrelevant Attributes Abound: A New Linear-threshold Algorithm. Machine Learning, 285–318 (1988)Google Scholar
  21. 21.
    McCulloch, W.S., Pitts, W.H.: A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics 5, 115–133 (1943)MathSciNetzbMATHCrossRefGoogle Scholar
  22. 22.
    Shapire, R.E., Freund, Y.: Boosting. MIT Press, Cambridge (2012)Google Scholar
  23. 23.
    Leibbrandt, R.E., Powers, D.M.W.: Frequent frames as cues to part-of-speech in Dutch: why filler frequency matters. In: 32nd Annual Meeting of the Cognitive Science Society (CogSci 2010), pp. 2680–2685 (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • David M. W. Powers
    • 1
    • 2
  1. 1.CSEM Centre for Knowledge & Interaction TechnologyFlinders UniversityAdelaideAustralia
  2. 2.Beijing Municipal Lab for Multimedia & Intelligent SoftwareBJUTBeijingChina

Personalised recommendations