output
20022026
most citedMethods for Interpreting and Understanding Deep Neural Networks

2.8k citations

Showing 2018Show all

19 papers · 1 filter

cs.DS2018★ 3 cited

Optimal Algorithms for Scheduling under Time-of-Use Tariffs

Lin Chen, Nicole Megow, Roman Rischke +2

We consider a natural generalization of classical scheduling problems in which using a time unit for processing a job causes some time-dependent cost which must be paid in addition…

cs.CV2018★ 126 cited

Learning The Invisible: A Hybrid Deep Learning-Shearlet Framework for Limited Angle Computed Tomography

T. A. Bubba, G. Kutyniok, M. Lassas +4

The high complexity of various inverse problems poses a significant challenge to model-based reconstruction schemes, which in such situations often reach their limits. At the same…

eess.SP2018

URLLC Services in 5G - Low Latency Enhancements for LTE

Thomas Fehrenbach, Rohit Datta, Barış Göktepe +2

5G is envisioned to support three broad categories of services: eMBB, URLLC, and mMTC. URLLC services refer to future applications which require reliable data communications from o…

eess.SP2018★ 28 cited

Efficient Sum-of-Sinusoids based Spatial Consistency for the 3GPP New-Radio Channel Model

Stephan Jaeckel, Leszek Raschkowski, Frank Burkhardt +1

Spatial consistency was proposed in the 3GPP TR 38.901 channel model to ensure that closely spaced mobile terminals have similar channels. Future extensions of this model might inc…

cs.LG2018★ 28 cited

iNNvestigate neural networks!

Maximilian Alber, Sebastian Lapuschkin, Philipp Seegerer +7

In recent years, deep neural networks have revolutionized many application domains of machine learning and are key components of many critical decision or predictive processes. The…

cs.LG2018★ 262 cited

Explaining the Unique Nature of Individual Gait Patterns with Deep Learning

Fabian Horst, Sebastian Lapuschkin, Wojciech Samek +2

Machine learning (ML) techniques such as (deep) artificial neural networks (DNN) are solving very successfully a plethora of tasks and provide new predictive models for complex phy…

cs.IT2018★ 71 cited

Enhanced Machine Learning Techniques for Early HARQ Feedback Prediction in 5G

Nils Strodthoff, Barış Göktepe, Thomas Schierl +2

We investigate Early Hybrid Automatic Repeat reQuest (E-HARQ) feedback schemes enhanced by machine learning techniques as a path towards ultra-reliable and low-latency communicatio…

cs.LG2018★ 1 cited

Understanding Patch-Based Learning by Explaining Predictions

Christopher Anders, Grégoire Montavon, Wojciech Samek +1

Deep networks are able to learn highly predictive models of video data. Due to video length, a common strategy is to train them on small video snippets. We apply the deep Taylor /…

cs.CY2018★ 176 cited

Detecting and interpreting myocardial infarction using fully convolutional neural networks

Nils Strodthoff, Claas Strodthoff

Objective: We aim to provide an algorithm for the detection of myocardial infarction that operates directly on ECG data without any preprocessing and to investigate its decision cr…

q-bio.PE2018★ 2 cited

Multiplex Network Structure Enhances the Role of Generalized Reciprocity in Promoting Cooperation

Viktor Stojkoski, Zoran Utkovski, Elisabeth Andre +1

In multi-agent systems, cooperative behavior is largely determined by the network structure which dictates the interactions among neighboring agents. These interactions often exhib…

q-bio.PE2018★ 6 cited

The Role of Multiplex Network Structure in Cooperation through Generalized Reciprocity

Viktor Stojkoski, Zoran Utkovski, Elisabeth Andre +1

Recent studies suggest that the emergence of cooperative behavior can be explained by generalized reciprocity, a behavioral mechanism based on the principle of "help anyone if help…

eess.SP2018★ 48 cited

FDD massive MIMO channel spatial covariance conversion using projection methods

Lorenzo Miretti, Renato L. G. Cavalcante, Slawomir Stanczak

Knowledge of second-order statistics of channels (e.g. in the form of covariance matrices) is crucial for the acquisition of downlink channel state information (CSI) in massive MIM…

eess.SP2018★ 18 cited

Downlink channel spatial covariance estimation in realistic FDD massive MIMO systems

Lorenzo Miretti, Renato L. G. Cavalcante, Slawomir Stanczak

The knowledge of the downlink (DL) channel spatial covariance matrix at the BS is of fundamental importance for large-scale array systems operating in frequency division duplexing…

eess.SP2018

Spectral radii of asymptotic mappings and the convergence speed of the standard fixed point algorithm

Renato L. G. Cavalcante, Slawomir Stanczak

Important problems in wireless networks can often be solved by computing fixed points of standard or contractive interference mappings, and the conventional fixed point algorithm i…

q-bio.PE2018★ 12 cited

Cooperation dynamics of generalized reciprocity in state-based social dilemmas

Viktor Stojkoski, Zoran Utkovski, Lasko Basnarkov +1

We introduce a framework for studying social dilemmas in networked societies where individuals follow a simple state-based behavioral mechanism based on generalized reciprocity, wh…

physics.optics2018★ 79 cited

Silicon-plasmonic integrated circuits for terahertz signal generation and coherent detection

Tobias Harter, Sascha Muehlbrandt, Sandeep Ummethala +4

Optoelectronic signal processing offers great potential for generation and detection of ultra-broadband waveforms in the THz range, so-called T-waves. However, fabrication of the u…

cs.AI2018★ 6 cited

Dual Recurrent Attention Units for Visual Question Answering

Ahmed Osman, Wojciech Samek

Visual Question Answering (VQA) requires AI models to comprehend data in two domains, vision and text. Current state-of-the-art models use learned attention mechanisms to extract r…

physics.app-ph2018★ 15 cited

In-Situ 3D Nano-Printing of Freeform Coupling Elements for Hybrid Photonic Integration

P. -I. Dietrich, M. Blaicher, I. Reuter +9

Hybrid photonic integration exploits complementary strengths of different material platforms, thereby offering superior performance and design flexibility in comparison to monolith…

eess.SP2018★ 32 cited

Distributed Adaptive Learning with Multiple Kernels in Diffusion Networks

Ban-Sok Shin, Masahiro Yukawa, Renato Luis Garrido Cavalcante +1

We propose an adaptive scheme for distributed learning of nonlinear functions by a network of nodes. The proposed algorithm consists of a local adaptation stage utilizing multiple…