Skip to main content
SpringerLink
Log in
Book cover

International Conference on Hybrid Artificial Intelligence Systems

HAIS 2017: Hybrid Artificial Intelligent Systems pp 246–255Cite as

A Perceptron Classifier, Its Correctness Proof and a Probabilistic Interpretation

  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 10334))

Abstract

In this paper a fault tolerant probabilistic kernel version with smoothing parameter of Minsky’s perceptron classifier for more than two classes is exhibited and a correctness proof is provided. Moreover it is shown that the resulting classifier approaches optimality. Due to the non-determinism of the algorithm the (approximately) optimal value of a smoothing parameter has to be determined experimentally. The resulting complexity nevertheless allows for an efficient implementation employing for example Java concurrent programming and suitable hardware. In addition a probabilistic interpretation using Bayes Theorem is provided.

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

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

References

  1. Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, New York (2006)

    MATH  Google Scholar 

  2. Block, H.D., Levin, S.A.: On the boundedness of an iterative procedure for solving a system of linear inequalities. In: Proceedings of AMS (1970)

    Google Scholar 

  3. Cover, T.M.: Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition. IEEE Trans. Electr. Comput. 14, 326–334 (1965)

    Article  MATH  Google Scholar 

  4. Evgeniou, T., Pontil, M., Poggio, T.: Regularization networks and support vector machines. In: Smola, A.J., Bartlett, P.L., Schölkopf, B., Schuurmanns, D. (eds.) Advances in Large Margin Classifiers. MIT Press, Cambridge (2000)

    Google Scholar 

  5. Falkowski, B.-J.: Parallel implementation of certain neural network algorithms. In: Ruan, D., Montero, J., Martinez, L., D’hondt, P., Kerre, E. (eds.) Computational Intelligence in Decision and Control, Proceedings of the 8th International FLINS Conference. World Scientific, Singapore (2008)

    Google Scholar 

  6. Falkowski, B.-J.: Minsky revisited, fault tolerant perceptron learning with good generalization properties. In: Miller, L. (ed.) Proceedings of 30th international Conference on Computers and their Applications (CATA 2015). ISCA Publications (2015)

    Google Scholar 

  7. Falkowski, B.-J.: A perceptron classifier and corresponding probabilities. In: Ferraro, M.B., Giordani, P., Vantaggi, B., Gagolewski, M., Gil, M.Á., Grzegorzewski, P., Hryniewicz, O. (eds.) Soft Methods for Data Science. AISC, vol. 456, pp. 213–220. Springer, Cham (2017). doi:10.1007/978-3-319-42972-4_27

    Chapter  Google Scholar 

  8. Gallant, S.I.: Perceptron-based learning algorithms. IEEE Trans. Neural Netw. 1(2), 179–191 (1990)

    Article  MathSciNet  Google Scholar 

  9. Hands, D.P., Henley, W.E.: Statistical classification methods in consumer credit scoring: a review. J. R. Stat. Soc. Ser. A 160(3), 523–541 (1997)

    Article  Google Scholar 

  10. Kononenko, I.: Machine learning or medical diagnosis: history, state of the art, and perspective. AI Med. 23, 89–109 (2001)

    Google Scholar 

  11. Krauth, W., Mezard, M.: Learning algorithms with optimal stability in neural networks, J. Phys. A: Math. Gen. 20 (1987)

    Google Scholar 

  12. Meiring, G.A.M., Myburgh, H.C.: A review of intelligent driving style analysis systems and related AI algorithms, senses MDPI (2015)

    Google Scholar 

  13. Melvile, D., Webb, G.: Recommender systems. In: Samuel, C., Web, G. (eds.) Encyclopedia of Machine Learning. Springer, USA (2013)

    Google Scholar 

  14. Minsky, M.L., Papert, S.: Perceptrons, Expanded edn. MIT Press, Cambridge (1990)

    MATH  Google Scholar 

  15. Rojas, R.: Neural Networks. Springer, Berlin (1996)

    Book  MATH  Google Scholar 

  16. Shashua, A., Levin, A.: Ranking with large margin princple: two approaches. In: NIPS, vol. 14 (2003)

    Google Scholar 

  17. Shivani, A., Partha, N.: Generalization bounds for ranking alogorithms via algorithmic stability. J. Mach. Learn. Res. 10, 441–474 (2009)

    MATH  MathSciNet  Google Scholar 

  18. Schölkopf, B., Herbrich, R., Smola, A.J.: A generalized representer theorem. In: Helmbold, D., Williamson, B. (eds.) COLT 2001. LNCS, vol. 2111, pp. 416–426. Springer, Heidelberg (2001). doi:10.1007/3-540-44581-1_27

    Chapter  Google Scholar 

  19. Shawe-Taylor, J., Cristianini, N.: Kernel Methods for Pattern Analysis. CUP, New York (2004)

    Book  MATH  Google Scholar 

  20. Smola, A.J., Bartlett, P.L., Schölkopf, B., Schuurmanns, D.: Introduction to large margin classifiers. In: Smola, A.J., Bartlett, P.L., Schölkopf, B., Schuurmanns, D. (eds.) Advances in Large Margin Classifiers. MIT Press, Cambridge (2000)

    Google Scholar 

  21. Vapnik, V.N.: Statistical Learning Theory. Wiley, New York (1998)

    MATH  Google Scholar 

Download references

Acknowledgements

The author is indebted to M. Stern for help with some problems concerning the Java system.

Author information

Authors and Affiliations

  1. Fachhochschule für Ökonomie und Management FOM, Karlstrasse 2, 86150, Augsburg, Germany

    Bernd-Jürgen Falkowski

Authors
  1. Bernd-Jürgen Falkowski
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bernd-Jürgen Falkowski .

Editor information

Editors and Affiliations

  1. University of La Rioja , Logroño, La Rioja, Spain

    Francisco Javier Martínez de Pisón

  2. University of La Rioja , Logroño, La Rioja, Spain

    Rubén Urraca

  3. University of A Coruña , Ferrol, La Coruña, Spain

    Héctor Quintián

  4. University of Salamanca, Salamanca, Spain

    Emilio Corchado

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Falkowski, BJ. (2017). A Perceptron Classifier, Its Correctness Proof and a Probabilistic Interpretation. In: Martínez de Pisón, F., Urraca, R., Quintián, H., Corchado, E. (eds) Hybrid Artificial Intelligent Systems. HAIS 2017. Lecture Notes in Computer Science(), vol 10334. Springer, Cham. https://doi.org/10.1007/978-3-319-59650-1_21

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-59650-1_21

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-59649-5

  • Online ISBN: 978-3-319-59650-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation