Abstract. In this paper we introduce a new error measure, integrated reconstruction error (IRE) and show that the minimization of IRE leads to principal eigenvectors (without rotat...
Abstract. Non-negative sparse coding is a method for decomposing multivariate data into non-negative sparse components. In this paper we briefly describe the motivation behind this...
We explore how to improve machine translation systems by adding more translation data in situations where we already have substantial resources. The main challenge is how to buck ...
With the rapid rise of social media content, the question how people navigate to and from social media becomes important in order to understand what new tools and approaches are m...
Discovering non-trivial matching subsequences from two time series is very useful in synthesizing novel time series. This can be applied to applications such as motion synthesis wh...