A New Auto-associative Memory Based on Lattice Algebra

  • Gerhard X. Ritter
  • Laurentiu Iancu
  • Mark S. Schmalz
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3287)


This paper presents a novel, three-stage, auto-associative memory based on lattice algebra. The first two stages of this memory consist of correlation matrix memories within the lattice domain. The third and final stage is a two-layer feed-forward network based on dendritic computing. The output nodes of this feed-forward network yield the desired pattern vector association. The computations performed by each stage are all lattice based and, thus, provide for fast computation and avoidance of convergence problems. Additionally, the proposed model is extremely robust in the presence of noise. Bounds of allowable noise that guarantees perfect output are also discussed.


Associative Memory Lattice Domain Distorted Version Pattern Vector Perfect Recall 
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.


  1. 1.
    Ritter, G.X., Sussner, P., Diaz de Leon, J.L.: Morphological Associative Memories. IEEE Trans. on Neural Networks 9(2), 281–293 (1998)CrossRefGoogle Scholar
  2. 2.
    Ritter, G.X., Diaz de Leon, J.L., Sussner, P.: Morphological Bidirectional Associative Memories. Neural Networks 12, 851–867 (1999)CrossRefGoogle Scholar
  3. 3.
    Ritter, G.X., Urcid, G., Iancu, L.: Reconstruction of Noisy Patterns Using Morphological Associative Memories. J. of Mathematical Imaging and Vision 19(2), 95–111 (2003)zbMATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Urcid, G., Ritter, G.X., Iancu, L.: Kernel Computation in Morphological Bidirectional Associative Memories. In: Sanfeliu, A., Ruiz-Shulcloper, J. (eds.) CIARP 2003. LNCS, vol. 2905, pp. 552–559. Springer, Heidelberg (2003)Google Scholar
  5. 5.
    Sussner, P.: Observations on Morphological Associative Memories and the Kernel Method. Neurocomputing 31, 167–183 (2000)CrossRefGoogle Scholar
  6. 6.
    Ritter, G.X., Iancu, L., Urcid, G.: Neurons, Dendrites, and Pattern Classification. In: Sanfeliu, A., Ruiz-Shulcloper, J. (eds.) CIARP 2003. LNCS, vol. 2905, pp. 1–16. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  7. 7.
    Ritter, G.X., Iancu, L.: Lattice Algebra Approach to Neural Networks and Pattern Classification. Pattern Recognition and Image Analysis 14(2), 190–197 (2004)Google Scholar
  8. 8.
    Ritter, G.X., Iancu, L.: Morphological Perceptrons. Preprint submitted to IEEE Trans. on Neural NetworksGoogle Scholar
  9. 9.
    Eccles, J.C.: The Understanding of the Brain. McGraw-Hill, New York (1977)Google Scholar
  10. 10.
    Koch, C., Segev, I. (eds.): Methods in Neuronal Modeling: From Synapses to Networks. MIT Press, Boston (1989)Google Scholar
  11. 11.
    McKenna, T., Davis, J., Zornetzer, S.F. (eds.): Single Neuron Computation. Academic Press, San Diego (1992)zbMATHGoogle Scholar
  12. 12.
    Mel, B.W.: Synaptic Integration in Excitable Dendritic Trees. J. of Neurophysiology 70, 1086–1101 (1993)Google Scholar
  13. 13.
    Rall, W., Segev, I.: Functional Possibilities for Synapses on Dendrites and Dendritic Spines. In: Edelman, G.M., Gall, E.E., Cowan, W.M. (eds.) Synaptic Function, pp. 605–636. Wiley, New York (1987)Google Scholar
  14. 14.
    Segev, I.: Dendritic Processing. In: Arbib, M. (ed.) The Handbook of Brain Theory and Neural Networks, pp. 282–289. MIT Press, Boston (1998)Google Scholar
  15. 15.
    Ritter, G.X., Urcid, G.: Lattice Algebra Approach to Single Neuron Computation. IEEE Trans. on Neural Networks 14(2), 282–295 (2003)CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Gerhard X. Ritter
    • 1
  • Laurentiu Iancu
    • 1
  • Mark S. Schmalz
    • 1
  1. 1.CISE DepartmentUniversity of FloridaGainesvilleUSA

Personalised recommendations