Advertisement

Recovery of Performance in a Partially Connected Associative Memory Network Through Coding

  • Kit Longden
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3696)

Abstract

Introducing partial connectivity to an associative memory network increases the variance of the dendritic sum distributions, reducing the performance. A coding scheme to compensate for this effect is considered, in which output patterns are self-organised by the network. It is shown using signal-to-noise ratio analysis that when the output patterns are self-organised the performance is greater than in a network with a higher connectivity and random patterns, in the regime of low connectivity and a high memory load. This analysis is supported by simulations. The self-organising network also outperforms the random network with input activity-dependent thresholding mechanisms in simulations.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Willshaw, D.J., Buneman, O.P., Longuet-Higgins, H.C.: Non-holographic associative memory. Nature 222(197), 960–962 (1969)CrossRefGoogle Scholar
  2. [2]
    Buckingham, J.: Delicate nets, faint recollections: a study of partially connected associative network memories. PhD thesis, Univ. Edinburgh (1991)Google Scholar
  3. [3]
    Marr, D.: Simple memory: a theory for archicortex. Phil. Trans. R. Soc. B. 262(841), 24–81 (1971)CrossRefGoogle Scholar
  4. [4]
    Buckingham, J., Willshaw, D.J.: On setting unit thresholds in an incompletely connected associative net. Network 4, 441–459 (1993)CrossRefGoogle Scholar
  5. [5]
    Graham, B., Willshaw, D.J.: Improving recall from an associative memory. Biol. Cybernetics 72, 337–346 (1995)zbMATHCrossRefGoogle Scholar
  6. [6]
    Freund, T.F., Buzsaki, G.: Interneurons of the Hippocampus. Hippocampus 6, 347–470 (1996)CrossRefGoogle Scholar
  7. [7]
    Dayan, P., Willshaw, D.J.: Optimizing synaptic learning rules in linear associative memories. Biol. Cybernet. 65(4), 253–265 (1991)zbMATHCrossRefGoogle Scholar
  8. [8]
    Treves, A.: Quantitative estimate of the information relayed by the Schaffer collaterals. J. Comp. Neuro. 2(3), 259–272 (1995)CrossRefMathSciNetGoogle Scholar
  9. [9]
    Brun, V.H., Otnass, M.K., Molden, S., Steffenach, H.A., Witter, M.P., Moser, M.B., Moser, E.I.: Place cells and place recognition maintained by direct entorhinal-hippocampal circuitry. Science 296(5576), 2243–2246 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Kit Longden
    • 1
  1. 1.Institute for Adaptive and Neural ComputationSchool of Informatics University of EdinburghEdinburghU.K

Personalised recommendations