The neocognitron is a hierarchical multilayered neural network proposed by Professor Kunihiko Fukushima. It has been used for handwritten character recognition and other pattern recognition tasks. The neocognitron is inspired from the model proposed by Hubel & Wiesel in 1959. They found two types of cells in visual primary cortex called simple cell and complex cell, and also proposed a cascading model of these two type of cells.

PropertyValue
dbpprop:abstract
  • The neocognitron is a hierarchical multilayered neural network proposed by Professor Kunihiko Fukushima. It has been used for handwritten character recognition and other pattern recognition tasks. The neocognitron is inspired from the model proposed by Hubel & Wiesel in 1959. They found two types of cells in visual primary cortex called simple cell and complex cell, and also proposed a cascading model of these two type of cells. The neocognitron is a natural extension of these cascading models. In the neocognitron, which consists of two types of cells called S-cell and C-cell, the local features are extracted by S-cells, and these features' deformation, such as local shifts, are tolerated by C-cells. Local features in the input are integrated gradually and classifying in the higher layers. The idea of local feature integration is in several other models such as LeNet and SIFT model.
  • Das Neocognitron ist ein hierarchisches mehrschichtiges künstliches neuronales Netz, welches von Professor Kunihiko Fukushima bereits 1980 entwickelt wurde. Seitdem wurde es immer wieder verbessert und an das visuelle Wahrnehmungssystem angepasst. Es kommt zum Beispiel bei der Erkennung handschriftlicher Zeichen und bei anderen Mustererkennungs-Aufgaben zum Einsatz.
dbpprop:date
  • April 2009
dbpprop:hasPhotoCollection
dbpprop:reference
dbpprop:wikiPageUsesTemplate
rdf:type
rdfs:comment
  • The neocognitron is a hierarchical multilayered neural network proposed by Professor Kunihiko Fukushima. It has been used for handwritten character recognition and other pattern recognition tasks. The neocognitron is inspired from the model proposed by Hubel & Wiesel in 1959. They found two types of cells in visual primary cortex called simple cell and complex cell, and also proposed a cascading model of these two type of cells.
  • Das Neocognitron ist ein hierarchisches mehrschichtiges künstliches neuronales Netz, welches von Professor Kunihiko Fukushima bereits 1980 entwickelt wurde. Seitdem wurde es immer wieder verbessert und an das visuelle Wahrnehmungssystem angepasst. Es kommt zum Beispiel bei der Erkennung handschriftlicher Zeichen und bei anderen Mustererkennungs-Aufgaben zum Einsatz.
rdfs:label
  • Neocognitron
  • Neocognitron
owl:sameAs
skos:subject
foaf:page
is dbpprop:redirect of
is owl:sameAs of