Model of neural visual system with self-organizing cells
This paper describes a model of a neural visual system of a higher animal, in which the capability of pattern recognition develops adaptively. To produce the adaptability, we adopted ``self-organizing cells, and with them modeled feature-detecting cells which were discovered by \textit{D. Hubel} and \textit{T. Wiesel} [J. Physiol. 160, 106- 154 (1962)] and whose plasticity was found by \textit{C. Blakemore} and \textit{G. Cooper} [Nature 228, 477-478 (1970)]. Combining the ``self-organizing cells and the learning principle of a Perceptron-type system, we constructed a model of the whole visual system. The model is also equipped with an eye movement control mechanism for gazing, which reduces the number of ``self-organizing cells required for pattern recognition, thus contributing to their quick self- organization. Computer simulation and an experiment using a hardware simulator showed that ``self-organizing cells quickly become sensitive to the features often seen and that the resulting system can classify patterns with a rather small number of feature-detecting cells.
- scientific article; zbMATH DE number 4035622
- scientific article; zbMATH DE number 125401
- Object recognition by artificial cortical maps
- A neural network model for the mechanism of feature-extraction. A self- organizing network with feedback inhibition
- Self-organisation of transformation-invariant detectors for constituents of perceptual patterns
- Neural network model of on-off units in the fly visual system: Simulations of dynamic behavior
- Formation of segregated regions of feature detecting cells in self- organizing nerve field
- Object recognition by artificial cortical maps
- scientific article; zbMATH DE number 3896718 (Why is no real title available?)
- scientific article; zbMATH DE number 4035622 (Why is no real title available?)
- A mathematical justification of the grandmother cell hypothesis in neurobiology
- scientific article; zbMATH DE number 1977172 (Why is no real title available?)
- scientific article; zbMATH DE number 4116011 (Why is no real title available?)
- Self-organization of control circuits for invariant fiber projections
- Visual Feature Extraction by a Multilayered Network of Analog Threshold Elements
- A neural network model for the mechanism of feature-extraction. A self- organizing network with feedback inhibition
- Self-calibrated collinearity detector
This page was built for publication: Model of neural visual system with self-organizing cells
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1108220)
