1 code implementation • 27 Sep 2019 • Roman Föll, Bernard Haasdonk, Markus Hanselmann, Holger Ulmer
In this paper we introduce several new Deep recurrent Gaussian process (DRGP) models based on the Sparse Spectrum Gaussian process (SSGP) and the improved version, called variational Sparse Spectrum Gaussian process (VSSGP).
1 code implementation • 6 Jun 2019 • Markus Hanselmann, Thilo Strauss, Katharina Dormann, Holger Ulmer
For reproducibility of the method, our synthetic data is publicly available.
no code implementations • 10 Oct 2018 • Andrej Junginger, Markus Hanselmann, Thilo Strauss, Sebastian Boblest, Jens Buchner, Holger Ulmer
Neural networks have proven their capabilities by outperforming many other approaches on regression or classification tasks on various kinds of data.
1 code implementation • 2 Nov 2017 • Roman Föll, Bernard Haasdonk, Markus Hanselmann, Holger Ulmer
Modeling sequential data has become more and more important in practice.
no code implementations • ICLR 2018 • Thilo Strauss, Markus Hanselmann, Andrej Junginger, Holger Ulmer
We propose to use ensemble methods as a defense strategy against adversarial perturbations.