The neocognitron is a hierarchical, multilayered artificial neural network proposed by Kunihiko Fukushima in 1979.
[3] Previously in 1969, he published a similar architecture, but with hand-designed kernels inspired by convolutions in mammalian vision.
The neocognitron consists of multiple types of cells, the most important of which are called S-cells and C-cells.
Local features in the input are integrated gradually and classified in the higher layers.
[11] For example, some types of neocognitron can detect multiple patterns in the same input by using backward signals to achieve selective attention.