Advertisement

Neural Network with Memory and Cognitive Functions

  • Janusz A. Starzyk
  • Yue Li
  • David D. Vogel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3696)

Abstract

This paper provides an analysis of a new class of distributed memories known as R-nets. These networks are similar to Hebbian networks, but are relatively sparsly connected. R-nets use simple binary neurons and trained links between excitatory and inhibitory neurons. They use inhibition to prevent neurons not associated with a recalled pattern from firing. They are shown to implement associative learning and have the ability to store sequential patterns, used in networks with higher cognitive functions. This work explores the statistical properties of such networks in terms of storage capacity as a function of R-net topology and employed learning and recall mechanisms.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Freund, T.F., Buzsáki, G.: Interneurons of the Hippocampus. Hippocampus 6, 347–470 (1996)CrossRefGoogle Scholar
  2. Marr, D.: Simple memory: a theory for archicortex. Philosophical Transaction of the Royal Society of London B 262, 23–81 (1971)CrossRefGoogle Scholar
  3. Sik, A., Tamamaki, N., Freund, T.F.: Complete axon arborization of a single CA3 pyramidal cell in the rat hippocampus, and its relationship with postsynaptic parvalbumin-containing interneurons. European Journal of Neuroscience 5, 1719–1728 (1993)CrossRefGoogle Scholar
  4. Vogel, D., Boos, W.: Sparsely connected, Hebbian networks with strikingly large storage capacities. Neural Networks 10, 671–682 (1997)CrossRefGoogle Scholar
  5. Vogel, D.: Auto-associative memory produced by disinhibition in a sparsely connected network. Neural Networks 11, 897–908 (1998)CrossRefGoogle Scholar
  6. Vogel, D.: A biologically plausible model of associative memory which uses disinhibition rather than long term potentiation. Brain cogn. 45, 212–228 (2001)CrossRefGoogle Scholar
  7. Vogel, D.: A neural network model of memory and higher cognitive functions. International Journal of Psychophysiology 55(1), 3–21 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Janusz A. Starzyk
    • 1
  • Yue Li
    • 1
  • David D. Vogel
    • 2
  1. 1.School of Electrical Engineering and Computer ScienceOhio UniversityAthensU.S.A
  2. 2.Ross University School of MedicineCommonwealth of Dominica

Personalised recommendations