Associative Learning in Hierarchical Self Organizing Learning Arrays

  • Janusz A. Starzyk
  • Zhen Zhu
  • Yue Li
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3696)


In this paper we introduce feedback based associative learning in self-organized learning arrays (SOLAR). SOLAR structures are hierarchically organized and have the ability to classify patterns in a network of sparsely connected neurons. These neurons may define their own functions and select their interconnections locally, thus satisfying some of the requirements for biologically plausible intelligent structures. Feed-forward processing is used to make necessary correlations and learn the input patterns. Associations between neuron inputs are used to generate feedback signals. These feedback signals, when propagated to the associated inputs, can establish the expected input values. This can be used for hetero and auto associative learning and pattern recognition.


Associative Learning Feedback Scheme Bidirectional Associative Memory Hopfield Network Solar Structure 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Rumelhart, D.E., McClelland, J.L., The PDP Research Group: Parallel Distributed Processing. MIT Press, Cambridge (1986)Google Scholar
  2. 2.
    Hecht-Nielsen, R.: Neurocomputing. Addison-Wesley, Reading (1990)Google Scholar
  3. 3.
    Kosko, B.: Bidirectional associative memories. IEEE Trans. Syst., Man, Cybern. 18, 49–60 (1988)CrossRefMathSciNetGoogle Scholar
  4. 4.
    Wang, L.: Multi-associative Neural Networks and Their Applications to Learning and Retrieving Complex Spatio-Temporal Sequences. IEEE Trans. Syst., Man, Cybern. 29(1) (February 1999)Google Scholar
  5. 5.
    Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Nat. Acad. Sci. USA 79, 2554–2558 (1982)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Vogel, D., Boos, W.: Sparsely connected, Hebbian networks with strikingly large storage capacities. Neural Networks 4(10), 671–682 (1997)CrossRefGoogle Scholar
  7. 7.
    Vogel, D.: Auto-associative memory produced by disinhibition in a sparsely connected network. Neural Networks 5(11), 897–908 (1998)CrossRefGoogle Scholar
  8. 8.
    Guyon, I., Personnaz, L., Nadal, J.P., Dreyfus, G.: Storage and retrieval of complex sequences in neural networks. Phys. Rev. A 38, 6365–6372 (1988)MathSciNetGoogle Scholar
  9. 9.
    Wang, D.L., Yuwono, B.: Anticipation-based temporal pattern generation. IEEE Trans. Syst., Man, Cybern. 25, 615–628 (1995)CrossRefGoogle Scholar
  10. 10.
    Wang, L.: Multi-associative neural networks and their applications to learning and retrieving complex spatio-temporal sequences. IEEE Trans. Syst., Man, Cybern., Part B 29(1), 73–82 (1999)CrossRefGoogle Scholar
  11. 11.
    Starzyk, J.A., Zhu, Z., Liu, T.-H.: Self-Organizing Learning Array. IEEE Trans. on Neural Networks 16(2), 355–363 (2005)CrossRefGoogle Scholar
  12. 12.
    Watts, D.J., Strogatz, S.H.: Collective dynamics of small-world networks. Nature 393, 440–442 (1998)CrossRefGoogle Scholar
  13. 13.
    Loh, W.-Y.: Teaching Assistant Evaluation, June 7 (1997), Available:
  14. 14.
    Fisher, R.A.: Iris Plants Database (July 1988), Available:
  15. 15.
    Andonie, R., Cat¸aron, A.: An Informational Energy LVQ Approach for Feature Ranking. In: Verleysen, M. (ed.) The European Symposium on Artificial Neural Networks (ESANN 2004), Bruges, Belgium, April 28-30, pp. 471–476. D-side publications (2004)Google Scholar
  16. 16.
    German, B.: Glass Identification Database (September 1987), Available:

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Janusz A. Starzyk
    • 1
  • Zhen Zhu
    • 1
  • Yue Li
    • 1
  1. 1.School of Electrical Engineering and Computer ScienceOhio UniversityAthensU.S.A

Personalised recommendations