output
20022026
most citedMethods for Interpreting and Understanding Deep Neural Networks

2.8k citations

Showing 2019Show all

21 papers · 1 filter

q-bio.PE2019★ 2 cited

Evolution of cooperation in networked heterogeneous fluctuating environments

Viktor Stojkoski, Marko Karbevski, Zoran Utkovski +2

Fluctuating environments are situations where the spatio-temporal stochasticity plays a significant role in the evolutionary dynamics. The study of the evolution of cooperation in…

cs.LG2019★ 267 cited

Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning

Seul-Ki Yeom, Philipp Seegerer, Sebastian Lapuschkin +4

The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to r…

cs.LG2019★ 76 cited

On the Explanation of Machine Learning Predictions in Clinical Gait Analysis

Djordje Slijepcevic, Fabian Horst, Sebastian Lapuschkin +6

Machine learning (ML) is increasingly used to support decision-making in the healthcare sector. While ML approaches provide promising results with regard to their classification pe…

cond-mat.stat-mech2019★ 115 cited

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…

cs.AI2019★ 576 cited

Towards Explainable Artificial Intelligence

Wojciech Samek, Klaus-Robert Müller

In recent years, machine learning (ML) has become a key enabling technology for the sciences and industry. Especially through improvements in methodology, the availability of large…

cs.LG2019★ 74 cited

Explaining and Interpreting LSTMs

Leila Arras, Jose A. Arjona-Medina, Michael Widrich +5

While neural networks have acted as a strong unifying force in the design of modern AI systems, the neural network architectures themselves remain highly heterogeneous due to the v…

cs.NI2019★ 13 cited

Power and Beam Optimization for Uplink Millimeter-Wave Hotspot Communication Systems

Rafail Ismayilov, Bernd Holfeld, Renato L. G. Cavalcante +1

We propose an effective interference management and beamforming mechanism for uplink communication systems that yields fair allocation of rates. In particular, we consider a hotspo…

eess.IV2019★ 167 cited

Resolving challenges in deep learning-based analyses of histopathological images using explanation methods

Miriam Hägele, Philipp Seegerer, Sebastian Lapuschkin +5

Deep learning has recently gained popularity in digital pathology due to its high prediction quality. However, the medical domain requires explanation and insight for a better unde…

cs.LG2019★ 114 cited

DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks

Simon Wiedemann, Heiner Kirchoffer, Stefan Matlage +10

The field of video compression has developed some of the most sophisticated and efficient compression algorithms known in the literature, enabling very high compressibility for lit…

cond-mat.mes-hall2019★ 5 cited

Nucleation at the phase transition near 40~C in MnAs nanodisks

B Jenichen, Y Takagaki, K H Ploog +3

The phase transition near 40~C of both as-grown thin epitaxial MnAs films prepared by molecular beam epitaxy on GaAs(001) and nanometer-scale disks fabricated from the s…

q-fin.ST2019★ 19 cited

Lead-lag Relationships in Foreign Exchange Markets

Lasko Basnarkov, Viktor Stojkoski, Zoran Utkovski +1

Lead-lag relationships among assets represent a useful tool for analyzing high frequency financial data. However, research on these relationships predominantly focuses on correlati…

cs.LG2019★ 113 cited

From Clustering to Cluster Explanations via Neural Networks

Jacob Kauffmann, Malte Esders, Lukas Ruff +3

A recent trend in machine learning has been to enrich learned models with the ability to explain their own predictions. The emerging field of Explainable AI (XAI) has so far mainly…

cs.LG2019★ 9 cited

Achieving Generalizable Robustness of Deep Neural Networks by Stability Training

Jan Laermann, Wojciech Samek, Nils Strodthoff

We study the recently introduced stability training as a general-purpose method to increase the robustness of deep neural networks against input perturbations. In particular, we ex…

eess.SP2019★ 42 cited

Tensor Completion for Radio Map Reconstruction using Low Rank and Smoothness

Daniel Schäufele, Renato L. G. Cavalcante, Slawomir Stanczak

Radio maps are important enablers for many applications in wireless networks, ranging from network planning and optimization to fingerprint based localization. Sampling the complet…

eess.SP2019★ 1 cited

Spatial Consistency Evaluation Based on Massive SIMO Measurements

Sida Dai, Martin Kurras

In this paper, the spatial consistency of wireless massive single-input-multiple-output channels in a cellular small cell scenario is evaluated based on measurements taken in Berli…

cond-mat.str-el2019★ 24 cited

Maltese Cross anisotropy in Ho0.8Lu0.2B12 antiferromagnetic metal with dynamic charge stripes

A. L. Khoroshilov, V. N. Krasnorussky, K. M. Krasikov +12

The model strongly correlated electron system Ho0.8Lu0.2B12 which demonstrates a cooperative Jahn-Teller instability of the boron sub-lattice in combination with rattling modes of…

cs.IT2019★ 9 cited

A Scalable Max-Consensus Protocol For Noisy Ultra-Dense Networks

Navneet Agrawal, Matthias Frey, Slawomir Stanczak

We introduce \emph{ScalableMax}, a novel communication scheme for achieving max-consensus in a network of multiple agents which harnesses the interference in the wireless channel a…

q-fin.ST2019★ 10 cited

Correlation Patterns in Foreign Exchange Markets

Lasko Basnarkov, Viktor Stojkoski, Zoran Utkovski +1

The value of an asset in a financial market is given in terms of another asset known as numeraire. The dynamics of the value is non-stationary and hence, to quantify the relationsh…

cs.AI2019★ 1k cited

Unmasking Clever Hans Predictors and Assessing What Machines Really Learn

Sebastian Lapuschkin, Stephan Wäldchen, Alexander Binder +3

Current learning machines have successfully solved hard application problems, reaching high accuracy and displaying seemingly "intelligent" behavior. Here we apply recent technique…

cs.CV2019★ 40 cited

Multi-Kernel Prediction Networks for Denoising of Burst Images

Talmaj Marinč, Vignesh Srinivasan, Serhan Gül +2

In low light or short-exposure photography the image is often corrupted by noise. While longer exposure helps reduce the noise, it can produce blurry results due to the object and…

nlin.AO2019★ 21 cited

Cooperation dynamics in the networked geometric Brownian motion

Viktor Stojkoski, Zoran Utkovski, Lasko Basnarkov +1

Recent works suggest that pooling and sharing may constitute a fundamental mechanism for the evolution of cooperation in well-mixed fluctuating environments. The rationale is that,…