Design of ART-based hierarchical clustering algorithm using quadratic junction neural networks

In this paper, Structure and properties of neural networks with quadratic junction are presented. Unsupervised learning rules about the neural networks are given. Using this kind of neural networks, an ART-based hierarchical clustering algorithm is suggested. The algorithm can determine the number of clusters and clustering data. The time and space complexity of the algorithm are discussed. A 2-D artificial data set is used to illustrate and compare the effectiveness of the proposed algorithm and K-means algorithm.