This paper presents a novel method for learning object manipulation such as rotating an object or placing one object on another. In this method, motions are learned using referenc...
Faces under varying illumination, pose and non-rigid deformation are empirically thought of as a highly nonlinear manifold in the observation space. How to discover intrinsic low-...
An important feature of many problem domains in machine learning is their geometry. For example, adjacency relationships, symmetries, and Cartesian coordinates are essential to an...