1 code implementation • 7 Dec 2020 • Ahcène Boubekki, Michael Kampffmeyer, Robert Jenssen, Ulf Brefeld
That simple neural network, referred to as the clustering module, can be integrated into a deep autoencoder resulting in a deep clustering model able to jointly learn a clustering and an embedding.
no code implementations • 22 Oct 2020 • Samuel G. Fadel, Sebastian Mair, Ricardo da S. Torres, Ulf Brefeld
In this paper, we solve this issue by enforcing a fixed norm and, hence, change the base distribution, to allow for a principled way of interpolation.
no code implementations • NeurIPS Workshop ICBINB 2020 • Yannick Rudolph, Ulf Brefeld, Uwe Dick
Given a neural network with a graph architecture and/or structured output function, variational autoencoding does not seem to contribute statistically significantly to empirical performance.
1 code implementation • NeurIPS 2019 • Sebastian Mair, Ulf Brefeld
Archetypal analysis represents instances as linear mixtures of prototypes (the archetypes) that lie on the boundary of the convex hull of the data.
no code implementations • ICLR 2019 • Uwe Dick, Maryam Tavakol, Ulf Brefeld
We study credit assignment problems in spatial multi-agent environments where agents pursue a joint objective.
no code implementations • ICML 2017 • Sebastian Mair, Ahcène Boubekki, Ulf Brefeld
Archetypal Analysis is the method of choice to compute interpretable matrix factorizations.
no code implementations • 19 Jun 2017 • Jan Reubold, Thorsten Strufe, Ulf Brefeld
We propose a Bayesian nonparametric mixture model for prediction- and information extraction tasks with an efficient inference scheme.
no code implementations • 23 Jan 2014 • Nico Goernitz, Marius Micha Kloft, Konrad Rieck, Ulf Brefeld
Anomaly detection is being regarded as an unsupervised learning task as anomalies stem from adversarial or unlikely events with unknown distributions.
no code implementations • NeurIPS 2009 • Marius Kloft, Ulf Brefeld, Pavel Laskov, Klaus-Robert Müller, Alexander Zien, Sören Sonnenburg
Previous approaches to multiple kernel learning (MKL) promote sparse kernel combinations and hence support interpretability.