Immunity Clonal Synergetic Learning of Unbalanced Attention Parameters in Synergetic Network

摘要

In this paper, we discuss the dynamical behavior of synergetic neural network and propose a new unbalanced attention parameters optimization algorithm based on Immunity Clonal algorithm (ICA). In comparison with the algorithms with balanced attention parameters and that with unbalanced attention parameters on GA, the new method has automatic balance ability between exploration and exploitation and is not easy to get into local optimum. In addition, iterative step is adjusted adaptively. Experiments on textural images and remote sensing images show that the presented algorithm has not only faster convergent rate but also better recognition rate.