Biological Cybernetics

, Volume 20, Issue 3–4, pp 121–136 | Cite as

Cognitron: A self-organizing multilayered neural network

  • Kunihiko Fukushima
Article

Abstract

A new hypothesis for the organization of synapses between neurons is proposed: “The synapse from neuron x to neuron y is reinforced when x fires provided that no neuron in the vicinity of y is firing stronger than y”. By introducing this hypothesis, a new algorithm with which a multilayered neural network is effectively organized can be deduced. A self-organizing multilayered neural network, which is named “cognitron”, is constructed following this algorithm, and is simulated on a digital computer. Unlike the organization of a usual brain models such as a three-layered perceptron, the self-organization of a cognitron progresses favorably without having a “teacher” which instructs in all particulars how the individual cells respond. After repetitive presentations of several stimulus patterns, the cognitron is self-organized in such a way that the receptive fields of the cells become relatively larger in a deeper layer. Each cell in the final layer integrates the information from whole parts of the first layer and selectively responds to a specific stimulus pattern or a feature.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Blakemore, C., Cooper, G.F.: Development of the brain depends on the visual environment. Nature (Lond.), 228, 477–478 (1970)Google Scholar
  2. Block, H.D., Knight, B.W., Rosenblatt, F.: Analysis of four-layer series-coupled perceptron. II. Rev. mod. Phys. 34, 135–142 (1962)Google Scholar
  3. Fukushima, K.: Visual feature extraction by a multilayered network of analog threshold elements. IEEE Trans. Syst. Sci. Cybernetics SSC-5, 322–333 (1969)Google Scholar
  4. Fukushima, K.: A feature extractor for curvilinear patterns: A design suggested by the mammalian visual system. Kybernetik 7, 153–160 (1970)Google Scholar
  5. Fukushima, K.: A feature extractor for a pattern recognizer. A design suggested by the visual system (in Japanese). NHK Techn. J. 23, 351–367 (1971)Google Scholar
  6. Fukushima, K.: Self-organizing multilayered neuron network “Cognitron” (in Japanese), Paper of Technical Group on Pattern Recognition and Learning, Inst. Electronics Comm. Engrs. Japan, PRL74-25 (1974); and 1974 Nat. Conv. Rec. of Inst. Electronics Commun. Engrs. Japan, No. S9-8 (1974)Google Scholar
  7. Hubel, D.H., Wiesel, T.N.: Receptive fields of single neurones in the cat's visual cortex. J. Physiol. (Lond.) 148, 574–591 (1959)Google Scholar
  8. Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction and functional architecture in the cat's visual cortex. J. Physiol. (Lond.). 160, 106–154 (1962)Google Scholar
  9. Hubel, D.H., Wiesel, T.N.: Receptive fields and functional architecture in two nonstriate visual areas (18 and 19) of the cat. J. Neurophysiol. 28, 229–289 (1965)Google Scholar
  10. Malsburg, C. von der: Self-organization of orientation sensitive cells in the striate cortex. Kybernetik 14, 85–100 (1973)Google Scholar
  11. Marr, D.: A theory of cerebeller cortex. J. Physiol. (Lond.) 202, 437–470 (1969)Google Scholar
  12. Marr, D.: A theory of cerebral neocortex. Proc. roy. Soc. Lond. Ser. B, 176, 161–234 (1970)Google Scholar
  13. Rosenblatt, F.: Principles of Neurodynamics, Washington: Spartan Books 1962Google Scholar

Copyright information

© Springer-Verlag 1975

Authors and Affiliations

  • Kunihiko Fukushima
    • 1
  1. 1.NHK Broadcasting Science Research LaboratoriesTokyoJapan

Personalised recommendations