Network Intrusion Detection System, Security mechanism has recently become vital component of IT world and system usage over the internet. As an effective technique to dealing with network difficulties, intrusion detection systems employ several classifiers to detect various types of attacks. The performance results are compared with several classifiers of neural network. Classifiers are employed with different five classifiers in this proposed study namely Elman Neural Network (ENN), Feed Forward Neural Network (FFNN), Probabilistic Neural Network (PNN), Radial Basis Neural Network (RBNN) and Generalized Regression Neural Network (GRNN). The feature decline approaches used to filter the specific KDD dataset in this problem. The accuracy results of full-features and reduced features datasets are matched.