The Application of Immune Genetic Algorithm in BP Neural Network

Randomly generating the initial weights and thresholds of the neural network will bring uncertainty to the network. We used genetic algorithms to optimize the initial weights and thresholds of the neural network. However, the genetic algorithm may have the problem of premature population maturity during its operation, that is, the algorithm has converged before reaching the global optimal solution. To this end, the immune genetic algorithm is used to optimize the initial weights and thresholds of the neural network to avoid premature maturity of the population. A binary classification problem model is established. From the simulation training results, the use of immune genetic algorithm to optimize the BP neural network can more effectively prevent the network from falling into a local minimum during training, improve the network convergence speed, and complete it more accurately and stably Two classification problems.