A Genetic-Algorithm-based Two-Stage Learning Scheme for Neural Networks
Cai Kai-yuan · Acta Simulata Systematica Sinica · 2003
A two-stage learning scheme for neural networks is proposed in this paper. In the first stage, which is 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.