Self-organizing architecture for learning novel patterns

✍ Scribed by Kouichirou Yamauchi; Takashi Jimbo; Masayoshi Umeno

• Book ID: 104591491
• Publisher: John Wiley and Sons
• Year: 1992
• Tongue: English
• Weight: 811 KB
• Volume: 23
• Category: Article
• ISSN: 0882-1666
• DOI: 10.1002/scj.4690230404

✦ Synopsis

Abstract

Although the neuron model is very useful for many applications, it has a serious problem of learning. For example, a neuron model for pattern recognition works well after learning, but it must be retrained on all sample patterns if a new category of patterns is added. On the other hand, humans can add the new category immediately, without relearning all the old patterns. To solve this problem, we propose a new self‐organizing architecture for learning novel patterns. This model can learn novel patterns as soon as they are recognized to be new, just like humans do.