An Unbalanced Parameters Optimization of Synergetic Neural Network based on Differential Evolution Algorithm

Synergetic pattern recognition method is a novel approach to pattern recognition based on synergetic principles. We could improve recognition performance of SNN (Synergetic Neural Network) by adjusting attention parameters in the neural network system. The unbalanced parameters of Synergetic neural network are optimized to improve the recognition effect by sufficiently using the self-learning abilities of SNN. Differential evolution, as an effective searching algorithm for global approximate optimal solution, has the characteristics of convergence fast to better solution. In this paper, an algorithm of parameters optimization based on differential evolution was proposed. This new algorithm is used to search the global optimum attention parameters of SNN in the corresponding parameter space. Fitness mean square variance is adopted to modify searching speed and searching precision in the adaptive manner, because the parameters of differential evolution algorithm are hard to adopt dynamically. and the way of fitness mean square variance could helps improving the optimizing abilities of the algorithm. The new algorithm has better parameter searching abilities, both globally and locally, and can hardly been trapped into local extreme. A simplified version of the order parameter set is applied in this algorithm which improves the recognition ratio of the SNN system effectively. Experiment result on real images show that the change of attention parameters could lead to completely different recognition results. Comparisons with the algorithm under balanced attention parameters and with other optimization algorithm under unbalanced attention parameters are made and the proposed algorithm has faster convergent speed and better recognition result.