Incorporating Scale Invariance into the Cellular Associative Neural Network

  • Nathan Burles
  • Simon O’Keefe
  • James Austin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8681)


This paper describes an improvement to the Cellular Associative Neural Network, an architecture based on the distributed model of a cellular automaton, allowing it to perform scale invariant pattern matching. The use of tensor products and superposition of patterns allows the system to recall patterns at multiple resolutions simultaneously. Our experimental results show that the architecture is capable of scale invariant pattern matching, but that further investigation is needed to reduce the distortion introduced by image scaling.


pattern recognition scale invariance associative memory correlation matrix memory distributed computation cellular automata 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Preston, K., Duff, M. (eds.): Modern Cellular Automata: Theory and Applications. Plenum Press (1984)Google Scholar
  2. 2.
    de Saint-Pierre, T., Milgram, M.: New and Efficient Cellular Algorithms for Image Processing. CVGIP: Image Understanding 55(3), 261–274 (1992)CrossRefzbMATHGoogle Scholar
  3. 3.
    Chua, L.O., Yang, L.: Cellular Neural Networks: Theory. IEEE Trans. on Circuits and Systems 35(10), 1257–1272 (1988)CrossRefzbMATHMathSciNetGoogle Scholar
  4. 4.
    Orovas, C., Austin, J.: Cellular Associative Neural Networks for Image Interpretation. In: Int. Conf. on Image Processing and its Appl., pp. 665–669. IET (1997)Google Scholar
  5. 5.
    Ballard, D.H.: Generalizing the Hough Transform to Detect Arbitrary Shapes. Pattern Recognition 13(2), 111–122 (1981)CrossRefzbMATHGoogle Scholar
  6. 6.
    Leung, T.K., Burl, M.C., Perona, P.: Finding Faces in Cluttered Scenes Using Random Labeled Graph Matching. In: Int. Conf. on Comput. Vis., pp. 637–644. IEEE (1995)Google Scholar
  7. 7.
    Wolfson, H.J., Rigoutsos, I.: Geometric Hashing: An Overview. Comput. Sci. & Eng. 4(4), 10–21 (1997)Google Scholar
  8. 8.
    Mokhtarian, F., Mackworth, A.K.: A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves. IEEE Trans. on Pattern Anal. and Mach. Intell. 14(8), 789–805 (1992)CrossRefGoogle Scholar
  9. 9.
    Burles, N., O’Keefe, S., Austin, J.: Improving the Associative Rule Chaining Architecture. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E.P., Appollini, B., Kasabov, N. (eds.) ICANN 2013. LNCS, vol. 8131, pp. 98–105. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  10. 10.
    Willshaw, D.J., Buneman, O.P., Longuet-Higgins, H.C.: Non-holographic Associative Memory. Nature 222, 960–962 (1969)CrossRefGoogle Scholar
  11. 11.
    Ritter, H., Martinetz, T., Schulten, K.: Neural Computation and Self-Organizing Maps: An Introduction. Addison-Wesley, Redwood City (1992)zbMATHGoogle Scholar
  12. 12.
    Burles, N., Austin, J., O’Keefe, S.: Extending the Associative Rule Chaining Architecture for Multiple Arity Rules. In: Neural-Symb. Learn. and Reason., Beijing, pp. 47–51 (2013)Google Scholar
  13. 13.
    Brewer, G.: Spiking Cellular Associative Neural Networks for Pattern Recognition. PhD Thesis, Univ. of York (2008)Google Scholar
  14. 14.
    Smolensky, P.: Tensor Product Variable Binding and the Representation of Symbolic Structures in Connectionist Systems. Artif. Intell. 46(1), 159–216 (1990)zbMATHMathSciNetGoogle Scholar
  15. 15.
    Stewart, T., Eliasmith, C.: Compositionality and Biologically Plausible Models. In: Werning, M., Hinzen, W., Machery, E. (eds.) The Oxf. Handb. of Compositionality. Oxford University Press, Oxford (2012)Google Scholar
  16. 16.
    Austin, J., Hobson, S., Burles, N., O’Keefe, S.: A Rule Chaining Architecture Using a Correlation Matrix Memory. In: Villa, A.E.P., Duch, W., Érdi, P., Masulli, F., Palm, G. (eds.) ICANN 2012, Part I. LNCS, vol. 7552, pp. 49–56. Springer, Heidelberg (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Nathan Burles
    • 1
  • Simon O’Keefe
    • 1
  • James Austin
    • 1
  1. 1.Department of Computer ScienceUniversity of YorkYorkUK

Personalised recommendations