A novel algorithm of neural network optimized design

Optimized design of neural network based on Immune modulated symbiotic evolution (IMSE) is proposed, which combines the adjustment of antibody of immune modulated theory so as to keep the individual diversity, with combining evolved intergrowth algorithm and density of immune principle suppress regulation mechanism together, system has shortened the individual's length of code and lightened the calculating amount by solving the evolution of the colony to the neuron part, eliminates the premature convergence effectively. Meanwhile, system adopts the improved immune adjustment algorithm, which improved the variety of the colony effectively. The neuron that produced in the colony in this way can get and realize the network quickly, which is controlled by the thick and shape of the board. The results of simulation experiment applies in AGC-ASC system of the two stands reversing tandem cold mill show that this method is suited to the complicated climate, and has good convergence and resisting disturbance.