A study of association model based on synergetics
Masahiro Marshall Nakagawa · 2005
In this study we show an association process of synergetic neural networks. The present association model is based on a top down formulation of the dynamic rule of analogue neural network. It is found that a complete association can be accomplished up to the same number of the embedded patterns as the number of neurons. In practice an association process is simulated for the practical images with 256 gray scale levels and 256/spl times/256 size. In addition, searching process of the embedded patterns is also realized by means of controlling the attraction parameters. Finally a stochastic model for the dynamic process is also proposed for the association and the searching of the embedded patterns.