Genetic algorithms and evolutionary programming hybrid strategy for structure and weight learning for multilayer feedforward neural networks

A hybrid strategy (GAs-EP) combining genetic algorithms (GAs) and evolutionary programming (EP) via a matrix group encoding is proposed to evolve a multilayer feedforward neural network, through simultaneously acquiring the network structure and weights. The strategy uses EP for evolving neural network and GAs for diversifying the individuals of the neural network population. This strategy inherits the strengths and suppresses the shortcomings of GAs and EP in their separate forms. The resulting strategy is simple and practical, and it has fast convergence. Its effectiveness has been demonstrated through its application to the polymer melt temperature prediction of injection molding.