(193), Max Planck Institute for Biological Cybernetics, Tübingen, Germany, September 2010 (Technical Report)
We introduce several new formulations for sparse nonnegative matrix approximation. Subsequently,
we solve these formulations by developing generic algorithms. Further, to help selecting a particular sparse formulation,
we briefly discuss the interpretation of each formulation. Finally, preliminary experiments are presented
to illustrate the behavior of our formulations and algorithms.
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems