A new strategy of dynamic change learning rate in BP neural network was proposed, it changes the learning rate value according to the change of system error between last iteration and this. The method improves the learning rate in BP network. The validity of dynamic change learning rate strategy in BP neural network has been showed by the experiments. In order to improve the detection efficiency of intrusion detection system, a new intrusion detection model was presented, it applies BP neural network based on dynamic change learning rate strategy and combines with the simulated annealing algorithm aim at optimizing intrusion detection system. Finally, the tests show the intrusion detection model improves the detection efficiency.
展开▼
