Neocognitron

The neocognitron is a hierarchical multi-layered artificial neural network , which was developed by Kunihiko Fukushima in 1980. Since then it has been continuously improved and adapted to the visual perception system. It is used, for example, to recognize handwritten characters and other pattern recognition tasks.

Web links

• Detailed Neocognitron elaboration on linux-related.de (PDF file; 1.10 MB)
• Article . In: Scholarpedia . (English, including references)
• Neocognitron on the Visiome Platform - C source code
• Neocognitron application (C #) and video about this simulator: here