Abstract
In a recent paper, Kunihiko Fukushima described a “Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position”. The present paper presents a simplified version of the neocognitron. Whereas the latter employs a 16 x 16-element visual field which requires computer simulation, the simplified model uses a 10-element one-dimensional visual field. Two input examples are analyzed: a white sheet which is gradually lowered over a black background, and a white center dot which gradually stretches vertically in both directions until it covers the balck background. The model demonstrates invariance with respect to lateral shift.
Similar content being viewed by others
References
Fukushima, K.: Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern.36, 193–202 (1980)
Hubel, D.H., Wiesel, T.N.: Brain mechanisms of vision. Sci. Am.241, 130–144 (1979)
Ruch, T.C.: Vision and the retina. In: Physiology and biophysics-the brain and neural function. Ruch, T.C., Patton, H.D. (eds.), p. 493. Philadelphia: Saunders Co. 1979
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Deutsch, S. A simplified version of Kunihiko Fukushima's neocognitron. Biol. Cybern. 42, 17–21 (1981). https://doi.org/10.1007/BF00335154
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF00335154