Research And Application Of Neural Networks Based On Genetic Algorithm

Artificial neural network is a jumped-up science simulating structure and mechanism ofhuman beings' brain. It is not comprehensive description of our brain but abstract simulation andpredigesting, aiming to explore the way of process, access and search information to find a newapproach to develop artificial intelligence and other sciences. Artificial neural network simulatesprinciple of nerve cell, has ability of self-study, association, contrast, ratiocination andrecapitulation.John Holland first brought genetic algorithm forward in 1975. Genetic algorithm is a kindof adaptive search strategy. Because genetic algorithm is adaptation, parallelism, and good atdealing with huge data, it is widely used in many fields. Therefore, genetic algorithm is used totrain artificial neural network to improve topology and weight of network. In practice,application of genetic algorithm to evolve BP network is more and more mature and gets goodresults. In contrast, though some achievements appear combination of genetic and fuzzy neuronnetwork need to be prospered.This paper uses the genetic algorithm to improve the parameters of the neural network.Form the experiment; we can get the conclusion that the genetic algorithm can improve theneural network efficiency. At last, an improved fuzzy neuron network based on genetic algorithmis put forward in this paper.