next up previous contents
Next: 目次

概要:

In this study the supplementary learning method in a chaotic neural network is devised. This network distinguishes an unknown pattern from the known patterns, and if it is the unknown pattern, the network performs supplementary learning.

When a known pattern is input into this network, it searches around the input pattern. In contrast, when an unknown pattern is input, the network shows chaotic movement between this pattern and learning pattern. Making use of the property, the network distinguishes an unknown pattern from the known patterns. Furthermore input pattern is given continuously, and outside input term is added. This network can learn a correct pattern from a unknown pattern with noise or an incomplete unknown pattern.

As supplementary learning method, there are global supplementary learning method or localized supplementary learning method. In this experiment we compare and examine them. Through computer simulations, the effectiveness of supplementary learning method is shown.





出口研究室へ

Deguchi Toshinori
1998年03月18日 (水) 13時22分42秒 JST