The Research of Dynamic Change Learning Rate Strategy in BP Neural Network and Application in Network Intrusion Detection

Authors:
Guangjun Song;Jialin Zhang;Zhenlong Sun
Affiliations:
-;-;-
Venue:
ICICIC '08 Proceedings of the 2008 3rd International Conference on Innovative Computing Information and Control
Year:
2008

Citing 0
Cited 3

Network Intrusion Detection with Workflow Feature Definition Using BP Neural Network

ISNN '09 Proceedings of the 6th International Symposium on Neural Networks on Advances in Neural Networks
Identification of nonlinear systems with outliers using wavelet neural networks based on annealing dynamical learning algorithm

Engineering Applications of Artificial Intelligence
Integration of support vector regression and annealing dynamical learning algorithm for MIMO system identification

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.