{"references": ["Hecht-Nielsen, R. (1988). Applications of counter propagation networks.\nNeural Networks, 1, 131-139.", "J. B. MacQueen (1967): \"Some Methods for classification and Analysis\nof Multivariate Observations, Proceedings of 5-th Berkeley Symposium\non Mathematical Statistics and Probability\", Berkeley, University of\nCalifornia Press, 1:281-297.", "E. M. Johansson, F. U. Dowla and D. M. Goodman, \"Backpropagation\nLearning for Multilayer Feed-forward Neural Networks using the\nConjugate Gradient Method'', Int. J. Neur. Syst. 2, 291 (1992).", "KDD data set, 1999;\nhttp://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html, cited April\n2003.", "Levin I.: KDD-99 Classifier Learning Contest LLSoft-s Results\nOverview. SIGKDD Explorations. ACM SIGKDD. 1(2) (2000) 67- 75.", "Kayacik G., Zincir-Heywood N., and Heywood M. On the Capability of\nan SOM based Intrusion Detection System. In Proceedings of\nInternational Joint Conference on Neural Networks, 2003.", "Dong Song, Malcolm I. Heywood, and A. Nur Zincir-Heywood.\n\"Training Genetic Programming on Half a Million Patterns: An Example\nfrom Anomaly Detection\", IEEE Transactions on Evolutionary\nComputation, 9(3), pp 225-240, 2005.", "Application of Machine Learning Algorithms to KDD Intrusion\nDetection Dataset within Misuse Detection Context, Maheshkumar\nSabhnani, Gursel Serpen, Proceedings of the International Conference\non Machine Learning, Models, Technologies and Applications\n(MLMTA 2003), Las Vegas, NV, June 2003, pages 209-215.", "F. Provost, T. Fawcett, and R. Kohavi. The case against accuracy\nestimation for comparing induction algorithms. In Proceedings Of 15th\nInternational Conference On Machine Learning, pages 445-453, San\nFrancisco, Ca, 1998. Morgan Kaufmann.\n[10] C. Elkan, \"Results of the KDD-99 Classifier Learning\", SIGKDD\nExplorations, ACM SIGKDD, Jan 2000."]}

In the present work, we propose a new technique to enhance the learning capabilities and reduce the computation intensity of a competitive learning multi-layered neural network using the K-means clustering algorithm. The proposed model use multi-layered network architecture with a back propagation learning mechanism. The K-means algorithm is first applied to the training dataset to reduce the amount of samples to be presented to the neural network, by automatically selecting an optimal set of samples. The obtained results demonstrate that the proposed technique performs exceptionally in terms of both accuracy and computation time when applied to the KDD99 dataset compared to a standard learning schema that use the full dataset.