Skip to main content
Springer Nature Link
Log in

Absolute Capacities for Higher Order Associative Memory of Sequential Patterns

  • Conference paper
Knowledge-Based Intelligent Information and Engineering Systems (KES 2005)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 3683))

  • 1078 Accesses

Abstract

In the previous paper, we have shown the conventional capacity of higher order associative memory of sequential patterns. The definition of the capacity permits that some of the elements of the pattern are not recalled correctly. If we want to recall the patterns more correctly, then the definition is not always valid. The absolute capacity is known as the severe definition that almost all the elements of the pattern are recalled correctly. In this paper, we show the absolute capacities of higher order associative memory of sequential patterns. Further, the absolute capacities are compared with the conventional ones. Specifically, the relation between the capacity and the correlation are shown.

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

Access this chapter

Log in via an institution

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. Hertz, J., Krogh, A., Palmer, R.G.: Introduction to the Theory of Neural Computation. Perseus Books Publishing, Cambridge (1991)

    Google Scholar 

  2. Amari, S.: Statistical Neurodynamics of Various Versions of Correlation Associative Memory. In: Proceedings of IEEE conference on Neural Networks, vol. 1, pp. 633–640 (1988)

    Google Scholar 

  3. Okada, M.: Notions of Associative Memory and Sparse Coding. Neural Networks 9, 1429–1458 (1996)

    Article  MATH  MathSciNet  Google Scholar 

  4. Hamakawa, Y., Miyajima, H., Shigei, N., Tsuruta, T.: On Some Properties of Higher Order Correlation Associative Memory of Sequential Patterns. Journal of Signal Processing 8, 225–234 (2004)

    Article  Google Scholar 

  5. Miyajima, H., Shigei, N., Hamakawa, Y.: Higher Order Differential Correlation Associative Memory of Sequential Patterns. In: IJCNN 2004, vol. II, pp. 891–896 (2004)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Kagoshima University, 1-21-40 Korimoto, Kagoshima, 890-0065, Japan

    Hiromi Miyajima & Noritaka Shigei

Authors
  1. Hiromi Miyajima
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Noritaka Shigei
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. School of Business, La Trobe University, 3086, Melbourne, Victoria, Australia

    Rajiv Khosla

  2. Centre for SMART systems Engineering Research Centre, University of Brighton, BN2 4GJ, Moulsecoomb, Brighton, UK

    Robert J. Howlett

  3. School of Electrical and Information Engineering, Knowledge Based Intelligent Engineering Systems Centre, University of South Australia, 5095, Mawson Lakes, SA, Australia

    Lakhmi C. Jain

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Miyajima, H., Shigei, N. (2005). Absolute Capacities for Higher Order Associative Memory of Sequential Patterns. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2005. Lecture Notes in Computer Science(), vol 3683. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11553939_78

Download citation

  • DOI: https://doi.org/10.1007/11553939_78

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-28896-1

  • Online ISBN: 978-3-540-31990-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics