2 code implementations • 16 Nov 2017 • Mike Wu, Michael C. Hughes, Sonali Parbhoo, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez
The lack of interpretability remains a key barrier to the adoption of deep models in many applications.
1 code implementation • 30 Jan 2019 • Sebastian Mathias Keller, Maxim Samarin, Mario Wieser, Volker Roth
"Deep Archetypal Analysis" generates latent representations of high-dimensional datasets in terms of fractions of intuitively understandable basic entities called archetypes.
1 code implementation • 3 Feb 2020 • Sebastian Mathias Keller, Maxim Samarin, Fabricio Arend Torres, Mario Wieser, Volker Roth
The real-world applicability of the proposed method is demonstrated by exploring archetypes of female facial expressions while using multi-rater based emotion scores of these expressions as side information.
2 code implementations • NeurIPS 2023 • Marcello Massimo Negri, F. Arend Torres, Volker Roth
Studying conditional independence among many variables with few observations is a challenging task.
1 code implementation • NeurIPS 2020 • Mario Wieser, Sonali Parbhoo, Aleksander Wieczorek, Volker Roth
Our approach is based on the deep information bottleneck in combination with a continuous mutual information regulariser.
no code implementations • CVPR 2019 • Adam Kortylewski, Aleksander Wieczorek, Mario Wieser, Clemens Blumer, Sonali Parbhoo, Andreas Morel-Forster, Volker Roth, Thomas Vetter
In this work, we consider the problem of learning a hierarchical generative model of an object from a set of images which show examples of the object in the presence of variable background clutter.
no code implementations • ICLR 2018 • Aleksander Wieczorek, Mario Wieser, Damian Murezzan, Volker Roth
Building on that, we show how this transformation translates to sparsity of the latent space in the new model.
no code implementations • 1 Nov 2016 • Aleksander Wieczorek, Volker Roth
We propose a new method of discovering causal relationships in temporal data based on the notion of causal compression.
no code implementations • 6 Oct 2015 • Dinu Kaufmann, Sonali Parbhoo, Aleksander Wieczorek, Sebastian Keller, David Adametz, Volker Roth
This paper considers a Bayesian view for estimating a sub-network in a Markov random field.
no code implementations • 14 Apr 2015 • Julia E. Vogt, Marius Kloft, Stefan Stark, Sudhir S. Raman, Sandhya Prabhakaran, Volker Roth, Gunnar Rätsch
We present a novel probabilistic clustering model for objects that are represented via pairwise distances and observed at different time points.
no code implementations • 6 Jul 2018 • Sonali Parbhoo, Mario Wieser, Aleksander Wieczorek, Volker Roth
Estimating the causal effects of an intervention from high-dimensional observational data is difficult due to the presence of confounding.
no code implementations • 19 Nov 2018 • Adam Kortylewski, Mario Wieser, Andreas Morel-Forster, Aleksander Wieczorek, Sonali Parbhoo, Volker Roth, Thomas Vetter
Computer vision tasks are difficult because of the large variability in the data that is induced by changes in light, background, partial occlusion as well as the varying pose, texture, and shape of objects.
no code implementations • 26 Nov 2018 • Sonali Parbhoo, Mario Wieser, Volker Roth
Estimating the causal effects of an intervention in the presence of confounding is a frequently occurring problem in applications such as medicine.
no code implementations • NeurIPS 2014 • David Adametz, Volker Roth
We present an inference method for Gaussian graphical models when only pairwise distances of n objects are observed.
no code implementations • NeurIPS 2012 • Melanie Rey, Volker Roth
We present a reformulation of the information bottleneck (IB) problem in terms of copula, using the equivalence between mutual information and negative copula entropy.
no code implementations • NeurIPS 2011 • David Adametz, Volker Roth
A Bayesian approach to partitioning distance matrices is presented.
no code implementations • 13 Aug 2019 • Mike Wu, Sonali Parbhoo, Michael Hughes, Ryan Kindle, Leo Celi, Maurizio Zazzi, Volker Roth, Finale Doshi-Velez
The lack of interpretability remains a barrier to the adoption of deep neural networks.
no code implementations • 14 Aug 2019 • Mike Wu, Sonali Parbhoo, Michael C. Hughes, Volker Roth, Finale Doshi-Velez
Moreover, for situations in which a single, global tree is a poor estimator, we introduce a regional tree regularizer that encourages the deep model to resemble a compact, axis-aligned decision tree in predefined, human-interpretable contexts.
no code implementations • 31 Dec 2019 • Aleksander Wieczorek, Volker Roth
The actual mutual information consists of the lower bound which is optimised in DVIB and cognate models in practice and of two terms measuring how much the former requirement $T-X-Y$ is violated.
no code implementations • 24 Jun 2020 • Maxim Samarin, Volker Roth, David Belius
The Neural Tangent Kernel (NTK) is an important milestone in the ongoing effort to build a theory for deep learning.
no code implementations • 8 Oct 2020 • Vitali Nesterov, Mario Wieser, Volker Roth
With the recent advances in machine learning for quantum chemistry, it is now possible to predict the chemical properties of compounds and to generate novel molecules.
1 code implementation • 25 Nov 2021 • Maxim Samarin, Vitali Nesterov, Mario Wieser, Aleksander Wieczorek, Sonali Parbhoo, Volker Roth
We address these shortcomings with a novel approach to cycle consistency.
no code implementations • 14 Apr 2022 • Vitali Nesterov, Fabricio Arend Torres, Monika Nagy-Huber, Maxim Samarin, Volker Roth
These networks represent functions that are guaranteed to have connected level sets forming smooth manifolds on the input space.
no code implementations • 3 Jun 2022 • Fabricio Arend Torres, Marcello Massimo Negri, Monika Nagy-Huber, Maxim Samarin, Volker Roth
Physics-informed Neural Networks (PINNs) have recently emerged as a principled way to include prior physical knowledge in form of partial differential equations (PDEs) into neural networks.
no code implementations • 26 May 2023 • F. Arend Torres, Marcello Massimo Negri, Marco Inversi, Jonathan Aellen, Volker Roth
We introduce Lagrangian Flow Networks (LFlows) for modeling fluid densities and velocities continuously in space and time.
no code implementations • 18 Aug 2023 • Monika Nagy-Huber, Volker Roth
Partial differential equations (PDEs) can describe many relevant phenomena in dynamical systems.