— To approximate complex data, we propose new type of low-dimensional “principal object”: principal cubic complex. This complex is a generalization of linear and nonlinear pr...
Alexander N. Gorban, Neil R. Sumner, Andrei Yu. Zi...
One way to address the continuing performance problem of high-level domain-specific languages, such as Octave or MATLAB, is to compile them to a relatively lower level language f...
Abstract. Hyperspectral imagery is a new type of high-dimensional image data which is now used in many Earth-based and planetary exploration applications. Many efforts have been d...
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
Tobias Jaeggli, Esther Koller-Meier, Luc J. Van Go...
Abstract. Feedback circuits are important for understanding the emergence of patterns of neural activity. In this contribution we study how a delayed circuit representing a recurre...
Cristina Masoller, M. C. Torrent, Jordi Garc&iacut...