(Submitted on 24 Feb 2014 ( v1 ), last revised plastik 28 Feb 2014 (this version, v2)) Abstract: Off

(Submitted on 24 Feb 2014 ( v1 ), last revised plastik 28 Feb 2014 (this version, v2)) Abstract: Off-the-shelf Gaussian Process (GP) covariance functions encode smoothness assumptions on the structure of the function to be modeled. plastik To model complex and non-differentiable plastik functions, these smoothness assumptions are often too restrictive. One way to alleviate this limitation is to find a different representation of the data by introducing a feature space. This feature plastik space is often learned in an unsupervised way, which might lead to data representations that are not useful for the overall regression task. In this paper, we propose Manifold Gaussian Processes, a novel supervised method that learns jointly a transformation of the data into a feature space and a GP regression from the feature space to observed space. The Manifold GP is a full GP, and it allows to learn data representations, which are useful for the overall regression task. As a proof-of-concept, we evaluate our approach on complex non-smooth functions where standard GPs perform poorly, such as step functions and effects of ground contacts in a robotics application.
Link back to: arXiv , form interface , contact .