Professor Kung gave a presentation on visualization of Big data from a component analysis perspective.
One of the most valuable means through which to make sense of big data, and thus make it more approachable and meaningful to most people, is through data visualization. Many algorithms have been proposed for high dimensional data visualization by both neural computing and statistics communities, most of which are based on a projection of the data onto a two or three dimensional space. Professor Kung introduced Canonical Vector Space in Principal Component Analysis (PCA), based on which we could develop Discriminant Component Analysis (DCA) and then even kernelize it. Compared to deep learning, which has become a household buzzword these days, DCA has solid theoretical foundations from the statistics community.