~2 min read
Encyclopedic overview
4 sectionsContents
- See also
- Notes
- References
- External links
__NOTOC__
The neocognitron is a hierarchical, multilayered artificial neural network proposed by Kunihiko Fukushima in 1979. It has been used for Japanese handwritten character recognition and other pattern recognition tasks, and served as the inspiration for convolutional neural networks.
Excerpted from Wikipedia’s “Neocognitron” article, available under the CC BY-SA 4.0 licence.