1982 | OriginalPaper | Buchkapitel
Neocognitron: A Self-Organizing Neural Network Model for a Mechanism of Visual Pattern Recognition
verfasst von : Kunihiko Fukushima, Sei Miyake
Erschienen in: Competition and Cooperation in Neural Nets
Verlag: Springer Berlin Heidelberg
Enthalten in: Professional Book Archive
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
A neural network model, called a “neocognitron”, is proposed for a mechanism of visual pattern recognition. It is demonstrated by computer simulation that the neocognitron has characteristics similar to those of visual systems of vertebrates.The neocognitron is a multilayered network consisting of a cascade connection of many layers of cells, and the efficiencies of the synaptic connections between cells are modifiable. Self-organization of the network progresses by means of “learning-without-a-teacher” process: Only repetitive presentation of a set of stimulus patterns is necessary for the self-organization of the network, and no information about the categories to which these patterns should be classified is needed. The neocognitron by itself acquires the ability to classify and correctly recognize these patterns according to the differences in their shapes: Any patterns which we human beings judge to be alike are also judged to be of the same category by the neocognitron. The neocognitron recognizes stimulus patterns correctly without being affected by shifts in position or even by considerable distortions in shape of the stimulus patterns. If a stimulus pattern is presented at a different position or if the shape of the pattern is distorted, the responses of the cells in the intermediate layers, especially the ones near the input layer, vary with the shift in position or the distortion in shape of the pattern. However, the deeper the layer is, the smaller become the variations in cellular responses. Thus, the cells of the deepest layer of the network are not affected by the shift in position or the distortion in shape of the stimulus pattern.