A Novel Hybrid Neural Network for Data Clustering

* Professor Sungyoung Lee is the corresponding author. Abstract Clustering plays an indispensable role for data analysis. Many clustering algorithms have been developed. However, most of them suffer either poor performance of unsupervised learning or lacking of mechanisms to utilize some prior knowledge about data (semi-supervised learning) for improving clustering result. In an effort to archieve the ability of semi-supervised clustering and better unsupervised clustering performance, we develop a hybrid neural network model (HNN). It is the sequential combination of Multi-Layer Perceptron (MLP) and Adaptive Resonance Theory-2 (ART2). It inherits two distinct advantages of stability and plasticity from ART2. Meanwhile, by combining the merits of MLP, it not only improves the performance for unsupervised clustering, but also supports for semi-supervised clustering if partial knowledge about data is available. Experiment results show that our model can be used both for unsupervised clustering and semi-supervised clustering with promising performance.