基于BP神经网络改进算法的入侵检测方法

对BP神经网络的算法进行改进：针对不同的训练样本，只激发网络中的部分神经元以产生输出。权值的调整只发生在与被激发的神经元相连弧线的权值上，而不是传统的BP神经网络需要对所有权值进行调整。实验结果表明，该算法在大样本训练网络时，可以显著提高网络的训练速度，减少训练的时间，同时还可以提高系统的检测率。

An Intrusion Detection Method Based on Improved BP Neural Network Algorithm

The BP neural network algorithm is improved to detect intrusion. The improved method is as follows: according to different input, different part of network will be fired to generate output. The weights of the arcs only connected with fired neuron will be adjusted whereas all weights in traditional BP network must be adjusted. The experiment results indicate that this improved algorithm can increase learning speed and shorten training time. The results also show that the intrusion detection rate is improved.