Learning the Similarity Preserving Principal Curves

The theory of Similarity Preserving Principal Curves (also called Principal Curves with Feature Continuity) has been studied. In this paper, we proposed a practical learning algorithm for learning the Similarity Preserving Principal Curves for a general data set. Furthermore, we proposed the concept and learning algorithms of the second-order Similarity Preserving Principal Curves. The learning algorithms are employed to extract efficient features for the data representation tasks. Experimental results show the ability of the proposed learning model and algorithms.