A Genetic-Algorithm-Based Two-Stage Learning Scheme for Neural Networks

In this paper, we propose A two-stage learning scheme for neural networks by integrating Gas into Structure identification £®In the first stage, which is also called structure identification stage, the selection of network structure and initial parameters is carried out by float genetic algorithm instead of human£®In the second stage£¬which is called parameter identification stage£¬the conventional optimization method is adopted to make refinements of parameters. Through the entire process, compromise is satisfactorily made among the network complexity, approximation accuracy and generalization ability£®