An IDS Detection Algorithm Based IBP Neural Network

摘要：

This paper discuss limitation of multi-ply feedback neural network algorithm, put forward a fast IDS detection algorithm based improved BP algorithm -IBP, new algorithm add a momentum item adopt alterable learn speed policy and batching, simulation with computer proves that choose bigger learning gcne can quicken algorithm convergent speed. The modified algorithm has some advantage than traditional algorithm in convergent speed, susceptive to begin coefficient, stabilization in network.

关键词： IBP algorithm convergent speed intrusion detection

作者: HAN Zhong-Xiang WANG Xiao-Dong HU Xi-Ming DUAN Tao

作者单位: The Telecommunication Engineering Institute Air Force Engineering University Xian, P.R.C

会议类型: 国际会议

会议名称: 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems(2010 IEEE 智能计算与智能系统国际会议 ICIS 2010)

会议地点: 厦门

会议语种:英文

页码: 698-701

在线出版日期: 2010-10-29（万方平台首次上网日期，不代表论文的发表时间）