activity
20182021
most citedFairwashing Explanations with Off-Manifold Detergent

35 citations · 61 across the 4 of their papers we have counts for

collaborators

9 papers

astro-ph.EP202116 cited

Deep learning for surrogate modelling of 2D mantle convection

Siddhant Agarwal, Nicola Tosi, Pan Kessel +2

Traditionally, 1D models based on scaling laws have been used to parameterized convective heat transfer rocks in the interior of terrestrial planets like Earth, Mars, Mercury and V…

cs.LG20204 cited

Towards Robust Explanations for Deep Neural Networks

Ann-Kathrin Dombrowski, Christopher J. Anders, Klaus-Robert Müller +1

Explanation methods shed light on the decision process of black-box classifiers such as deep neural networks. But their usefulness can be compromised because they are susceptible t…

cs.LG202035 cited

Fairwashing Explanations with Off-Manifold Detergent

Christopher J. Anders, Plamen Pasliev, Ann-Kathrin Dombrowski +2

Explanation methods promise to make black-box classifiers more transparent. As a result, it is hoped that they can act as proof for a sensible, fair and trustworthy decision-making…

hep-lat2020

Estimation of Thermodynamic Observables in Lattice Field Theories with Deep Generative Models

Kim A. Nicoli, Christopher J. Anders, Lena Funcke +5

In this work, we demonstrate that applying deep generative machine learning models for lattice field theory is a promising route for solving problems where Markov Chain Monte Carlo…

cond-mat.stat-mech2019

Asymptotically unbiased estimation of physical observables with neural samplers

Kim A. Nicoli, Shinichi Nakajima, Nils Strodthoff +3

We propose a general framework for the estimation of observables with generative neural samplers focusing on modern deep generative neural networks that provide an exact sampling p…

stat.ML2019

Explanations can be manipulated and geometry is to blame

Ann-Kathrin Dombrowski, Maximilian Alber, Christopher J. Anders +3

Explanation methods aim to make neural networks more trustworthy and interpretable. In this paper, we demonstrate a property of explanation methods which is disconcerting for both…