|
__NOTOC__ The neocognitron is a hierarchical, multilayered artificial neural network proposed by Kunihiko Fukushima in the 1980s. It has been used for handwritten character recognition and other pattern recognition tasks, and served as the inspiration for convolutional neural networks. The neocognitron was inspired by the model proposed by Hubel & Wiesel in 1959. They found two types of cells in the visual primary cortex called ''simple cell'' and ''complex cell'', and also proposed a cascading model of these two types of cells.〔Hubel and Wiesel 1959〕 The neocognitron is a natural extension of these cascading models. The neocognitron consists of multiple types of cells, the most important of which are called ''S-cells'' and ''C-cells.''〔Fukushima 1987, p. 83.〕 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 classified in the higher layers.〔Fukushima 1987, p. 84.〕 The idea of local feature integration is in several other models, such as ''LeNet'' and ''SIFT'' model. There are multiple kinds of neocognitron.〔Fukushima 2007〕 For example, some types of neocognitron can detect multiple patterns in the same input by using backward signals to achieve selective attention.〔Fukushima 1987, pp.81, 85〕 ==See also== *Self-organizing map *Artificial neural network *Pattern recognition *Unsupervised learning *Deep learning *Receptive field 抄文引用元・出典: フリー百科事典『 ウィキペディア（Wikipedia）』 ■ウィキペディアで「Neocognitron」の詳細全文を読む スポンサード リンク
|