Based On Two Types Of Neural Network Research

In recent years, artificial neural network, whose highly nonlinear, parallel, good fault tolerance and other advantages, in a multidisciplinary study has been widely used. After years of development, although the neural network is a more mature discipline, it has made remarkable progress, in course of the study, we found that some of the pitfalls inherent in neural networks has greatly limited its further development and application. For example, RBF neural network to the existence of prior vector number, the center vector itself is difficult to determine such defects, the neural network system model, neurons in the storage and transmission of information, the inevitable time lag phenomenon, it will not only reduce the network transmission speed, or even the entire network convergence, stability and accuracy is greatly influenced. Therefore, neural network research has a very important significance.Based on the above aspects, the two types of neural networks to study the issue, The first combined genetic algorithm and neural network advantages of each proposed combination of the two studies, and applied it to control, the expected good results. Again considering a class of delay artificial neural network model, stability analysis of the model, achieved a more relaxed conditions of practical criteria, an example to demonstrate the feasibility of the method.This article made about several aspects of research:(1) A comprehensive and systematic exposition of the current domestic and foreign combined neural network and genetic algorithm technology, and research on the delayed neural network research status, especially for RBF neural network core knowledge and based on Lyapunov stability theory in detail Introduction;(2) Analyzing the RBF neural network-specific, a genetic algorithm based on the RBF neural network algorithm, to optimize the center of the RBF neural network value;(3) Considering the analysis of a class of delay based on neural network model, the model's asymptotic stability in the equilibrium analysis, get a practical criterion;(4) We use the two experiments, the above mentioned algorithms and criterion validity, accuracy verification, experiments show that the achieved expected results.