output
20022025
most citedMethods for Interpreting and Understanding Deep Neural Networks

2.8k citations

Showing 2017Show all

74 papers · 1 filter

cond-mat.mtrl-sci20176 cited

Molecule signatures in photoluminescence spectra of transition metal dichalcogenides

Maja Feierabend, Gunnar Berghaeuser, Malte Selig +4

Monolayer transition metal dichalcogenides (TMDs) show an optimal surface-to-volume ratio and are thus promising candidates for novel molecule sensor devices. It was recently predi…

cs.LO20171 cited

Keep it Fair: Equivalences

Tobias Prehn, Stephan Mennicke

For models of concurrent and distributed systems, it is important and also challenging to establish correctness in terms of safety and/or liveness properties. Theories of distribut…

nlin.PS20179 cited

Chaotic bursting in semiconductor lasers

S. Ruschel, S. Yanchuk

We investigate the dynamic mechanisms for low frequency fluctuations in semiconductor lasers subject to delayed optical feedback, using the Lang-Kobayashi model. This system of del…

cond-mat.mes-hall2017180 cited

Phonon Sidebands in Transition Metal Dichalcogenides

Dominik Christiansen, Malte Selig, Gunnar Berghäuser +8

Excitons dominate the optical properties of monolayer transition metal dichalcogenides (TMDs). Besides optically accessible bright exciton states, TMDs exhibit also a multitude of…

cs.GT201713 cited

Multiwinner Elections with Diversity Constraints

Robert Bredereck, Piotr Faliszewski, Ayumi Igarashi +2

We develop a model of multiwinner elections that combines performance-based measures of the quality of the committee (such as, e.g., Borda scores of the committee members) with div…

stat.ML2017165 cited

The (Un)reliability of saliency methods

Pieter-Jan Kindermans, Sara Hooker, Julius Adebayo +5

Saliency methods aim to explain the predictions of deep neural networks. These methods lack reliability when the explanation is sensitive to factors that do not contribute to the m…