Biological Cybernetics

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

Cognitron: A self-organizing multilayered neural network

  • Kunihiko Fukushima


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.


Neural Network Individual Cell Deep Layer Receptive Field Final Layer 
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. 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