Neural Network Learning Improvement Using balance K-means

摘要

we present a Hierarchical clustering algorithm that balance k-means and Neural Network are used. In this paper there are three contributions. First the theory of the clustering algorithm is stated in detail. Second the steps of the algorithm are illustrated step by step. Third the results of experiments are reported in the end of the paper. The K-means algorithm is 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 experimental results obtained by applying this approach to the UCI datasets demonstrate that the proposed approach performs exceptionally in terms of both accuracy and computation time.