Hi, there are currently a number of unattended pull requests for sklearn on github in the area of Gaussian processes. If someone on the mailing list has experience with sklearn's implementation of GPs, it would be nice to get some feedback or get the PRs merged in.
Two PRs (https://github.com/scikit-learn/scikit-learn/pull/2798 and https://github.com/scikit-learn/scikit-learn/pull/2867) are essentially equivalent (they just differ in the unitttest); they fix a subtle bug in the GP hyperparameter optimization and could be easily merged in. PR 2930 (https://github.com/scikit-learn/scikit-learn/pull/2930) adds further correlation models for GPs and allows to estimate the noise level (nugget) from data. Some examples are given in the PR. Some feedback would be highly appreciated. Best, Jan -- Dipl.-Inform. Jan Hendrik Metzen Cognitive Robotics - Team Leader of Team "Learning" Universität Bremen und DFKI GmbH, Robotics Innovation Center FB 3 - Mathematik und Informatik AG Robotik Robert-Hooke-Straße 1 28359 Bremen, Germany Tel.: +49 421 178 45-4123 Zentrale: +49 421 178 45-6611 Fax: +49 421 178 45-4150 E-Mail: j...@informatik.uni-bremen.de Homepage: http://www.informatik.uni-bremen.de/~jhm/ Weitere Informationen: http://www.informatik.uni-bremen.de/robotik ------------------------------------------------------------------------------ _______________________________________________ Scikit-learn-general mailing list Scikit-learn-general@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
