Journal of Computer Science and Technology

, Volume 4, Issue 3, pp 204–217 | Cite as

On pattern separating function in a two-layered random nerve net with feedforward inhibitory connections

  • Toyoshi Torioka
  • Wang Jiaye 
Regular Papers


In this paper, we derive a theory for investigating the pattern separating function in the nerve net. Then, we consider some effects of the stochastic parameters constructing the nerve net, firing rates of the second layer and input patterns on the pattern separating function through the theory. As a result, we reveal that a nerve net excellent in pattern separating function is obtained when the stochastic parameters are selected properly. We also show that the pattern separating function is enhanced by controlling the firing rate of the second layer to a small value. Furthermore, the input patterns are separated largely when the firing rates of them are large.


Granule Cell Firing Rate Output Function Cerebellar Cortex Input Pattern 
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]
    J. S. Albus, A new approach to manipulator control: the cerebellar model articulation controller (CMAC),Trans. ASME, Ser. G,97 (1975), 220–227.MATHGoogle Scholar
  2. [2]
    S. Amari, A method of statical neurodynamics,Kybernetik,17 (1975), 228–233.MathSciNetGoogle Scholar
  3. [3]
    W. L. D. Barkowski and N. P. Larinova, Computer simulation of a cerebellar cortex compartment,Biol. Cybern.,51 (1985), 339–406.Google Scholar
  4. [4]
    J. C. Eccles, M. Ito and J. Zentagothai, The cerebellum as a neural machine. Berlin Heidelberg, New York: Springer, 1–226, 1967.Google Scholar
  5. [5]
    J. C. Eccles, K. Sasaki and P. Strata, A comparison of the inhibitory actions of Golgi cells and basket cells,Exp. Brain Res.,3 (1967), 81–94.Google Scholar
  6. [6]
    J. Hamori and J. Zentagothai, Participation of Golgi neuron process in the cerebellar glomeruli: an electron microscope study,Exp. Brain Res.,2 (1966), 35–48.CrossRefGoogle Scholar
  7. [7]
    Y. Kosugi and Y. Naito, Consideration on pattern separation in randomly-connected layered neural network,Trans. IECE Japan,58-D (1975), 539–547.Google Scholar
  8. [8]
    D. Marr, A theory of cerebellar cortex,J. Physiol.,202 (1969), 437–470.Google Scholar
  9. [9]
    J. E. Mittenthal, Reliabiltly of pattern separation by the cerebellar mossy fiber-granule cell system,Kyberntik,16 (1974), 93–101.CrossRefGoogle Scholar
  10. [10]
    M. Palkovits, P. Magyar and J. Zentagothai, Quantitative histological analysis of the cerebellar cortex in the cat. 11 cell numbers and densities the granule layer,Brain Res. 32 (1971) 15–30.CrossRefGoogle Scholar
  11. [11]
    T. Torioka, Pattern separability and the effect of the number of connections in a random neural net with inhibitory connections,Biol. Cybern.,31 (1978), 27–35.MATHCrossRefGoogle Scholar
  12. [12]
    T. Torioka, Pattern separating function in a random neural net with inhibitory connection.Biol Cybern.,34 (1979), 27–62.CrossRefGoogle Scholar
  13. [13]
    T. Torioka, and N. Ikeda, Pattern separating function of two-layered random nerve nets different in input-form,Tran. IECE Japan. 68-A (1985), 748–754.Google Scholar
  14. [14]
    T. Torioka, Pattern separating function of Two layered random nerve net receiving a fixed number of inputs,Trans. IECE Japan,69-D (1986), 1095–1102.Google Scholar
  15. [15]
    H. Wigström, A neuron model with learning capability and its relation to mechanism of assocation,Kyberntik,12 (1973), 399–406.Google Scholar
  16. [16]
    H. Wigström, Associative recall and formation of stable of activity model,J. Neuro. Research,1 (1975), 281–313.Google Scholar

Copyright information

© Science Press, Beijing China and Allerton Press Inc. 1989

Authors and Affiliations

  • Toyoshi Torioka
    • 1
  • Wang Jiaye 
    • 2
  1. 1.Technical CollegeYamaguchi UniversityJapan
  2. 2.Shandong UniversityJinan

Personalised recommendations