Advertisement

Biological Cybernetics

, Volume 36, Issue 4, pp 193–202 | Cite as

Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position

  • Kunihiko Fukushima
Article

Abstract

A neural network model for a mechanism of visual pattern recognition is proposed in this paper. The network is self-organized by “learning without a teacher”, and acquires an ability to recognize stimulus patterns based on the geometrical similarity (Gestalt) of their shapes without affected by their positions. This network is given a nickname “neocognitron”. After completion of self-organization, the network has a structure similar to the hierarchy model of the visual nervous system proposed by Hubel and Wiesel. The network consits of an input layer (photoreceptor array) followed by a cascade connection of a number of modular structures, each of which is composed of two layers of cells connected in a cascade. The first layer of each module consists of “S-cells”, which show characteristics similar to simple cells or lower order hypercomplex cells, and the second layer consists of “C-cells” similar to complex cells or higher order hypercomplex cells. The afferent synapses to each S-cell have plasticity and are modifiable. The network has an ability of unsupervised learning: We do not need any “teacher” during the process of self-organization, and it is only needed to present a set of stimulus patterns repeatedly to the input layer of the network. The network has been simulated on a digital computer. After repetitive presentation of a set of stimulus patterns, each stimulus pattern has become to elicit an output only from one of the C-cell of the last layer, and conversely, this C-cell has become selectively responsive only to that stimulus pattern. That is, none of the C-cells of the last layer responds to more than one stimulus pattern. The response of the C-cells of the last layer is not affected by the pattern's position at all. Neither is it affected by a small change in shape nor in size of the stimulus pattern.

Keywords

Pattern Recognition Neural Network Model Input Layer Complex Cell Digital Computer 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Fukushima, K.: Cognitron: a self-organizing multilayered neural network. Biol. Cybernetics 20, 121–136 (1975)Google Scholar
  2. Fukushima, K.: Improvement in pattern-selectivity of a cognitron (in Japanese). Pap. Tech. Group MBE78-27, IECE Japan (1978)Google Scholar
  3. Fukushima, K.: Self-organization of a neural network which gives position-invariant response (in Japanese). Pap. Tech. Group MBE 78-109, IECE Japan (1979a)Google Scholar
  4. Fukushima, K.: Self-organization of a neural network which gives position-invariant response. In: Proceedings of the Sixth International Joint Conference on Artificial Intelligence. Tokyo, August 20–23, 1979, pp. 291–293 (1979b)Google Scholar
  5. Fukushima, K.: Improvement in pattern-selectivity of a cognitron (in Japanese). Trans. IECE Japan (A), J 62-A, 650–657 (1979c)Google Scholar
  6. Giebel, H.: Feature extraction and recognition of handwritten characters by homogeneous layers. In: Pattern recognition in biological and technical systems. Grüsser, O.-J., Klinke, R. (eds.), pp. 162–169. Berlin, Heidelberg, New York: Springer 1971Google Scholar
  7. Gross, C.G., Rocha-Miranda, C.E., Bender, D.B.: Visual properties of neurons in inferotemporal cortex of the macaque. J. Neurophysiol. 35, 96–111 (1972)Google Scholar
  8. Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction and functional architecture in cat's visual cortex. J. Physiol. (London) 160, 106–154 (1962)Google Scholar
  9. Hubei, D.H., Wiesel, T.N.: Receptive fields and functional architecture in two nonstriate visual area (18 and 19) of the cat. J. Neurophysiol. 28, 229–289 (1965)Google Scholar
  10. Hubel, D.H., Wiesel, T.N.: Functional architecture of macaque monkey visual cortex. Proc. R. Soc. London, Ser. B 198, 1–59 (1977)Google Scholar
  11. Kabrisky, M.: A proposed model for visual information processing in the human brain. Urbana, London: Univ. of Illinois Press 1966Google Scholar
  12. Meyer, R.L., Sperry, R.W.: Explanatory models for neuroplasticity in retinotectral connections. In: Plasticity and function in the central nervous system. Stein, D.G., Rosen, J.J., Butters, N. (eds.), pp. 45–63. New York, San Francisco, London: Academic Press 1974Google Scholar
  13. Rosenblatt, F.: Principles of neurodynamics. Washington, D.C.: Spartan Books 1962Google Scholar
  14. Sato, T., Kawamura, T., Iwai, E.: Responsiveness of neurons to visual patterns in inferotemporal cortex of behaving monkeys. J. Physiol. Soc. Jpn. 40, 285–286 (1978)Google Scholar

Copyright information

© Springer-Verlag 1980

Authors and Affiliations

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

Personalised recommendations