Skip to Main Content
Considering that existing neural network's weights are randomly selected, hidden layer nodes are difficult to determine, the convergence speed is slow, and all these will easily lead to the problems such as local minimum values. In order to solve these problems, this article puts forward a kind of cooperative co-evolutionary genetic neural network. On the one hand, cooperative co-evolutionary genetic algorithm (CCGA) is introduced to optimize neural network structure, so as to solve the problem that the hidden neurons are difficult to determine, On the other hand, optimize neural network's connection weights, so as to improve the convergence speed and avoid falling into the local minimum values. The author established the model which is based on CCGA and so can simultaneously optimize the neural network's structure and weights. The algorithm is proved to be effective through the simulation experiment of stock forecast.
Date of Conference: 12-14 Jan. 2012