output
20022026
most citedMethods for Interpreting and Understanding Deep Neural Networks

2.8k citations

Showing 2021Show all

24 papers · 1 filter

cs.LG2021★ 113 cited

Toward Explainable AI for Regression Models

Simon Letzgus, Patrick Wagner, Jonas Lederer +3

In addition to the impressive predictive power of machine learning (ML) models, more recently, explanation methods have emerged that enable an interpretation of complex non-linear…

cs.CV2021★ 4 cited

Automated Damage Inspection of Power Transmission Towers from UAV Images

Aleixo Cambeiro Barreiro, Clemens Seibold, Anna Hilsmann +1

Infrastructure inspection is a very costly task, requiring technicians to access remote or hard-to-reach places. This is the case for power transmission towers, which are sparsely…

quant-ph2021★ 27 cited

Estimating gate-set properties from random sequences

J. Helsen, M. Ioannou, J. Kitzinger +4

With quantum computing devices increasing in scale and complexity, there is a growing need for tools that obtain precise diagnostic information about quantum operations. However, c…

math.OC2021★ 11 cited

The fixed point iteration of positive concave mappings converges geometrically if a fixed point exists: implications to wireless systems

Tomasz Piotrowski, Renato L. G. Cavalcante

We prove that the fixed point iteration of arbitrary positive concave mappings with nonempty fixed point set converges geometrically for any starting point. We also show that posit…

quant-ph2021★ 14 cited

Rate limits in quantum networks with lossy repeaters

Riccardo Laurenza, Nathan Walk, Jens Eisert +1

The derivation of ultimate limits to communication over certain quantum repeater networks have provided extremely valuable benchmarks for assessing near-term quantum communication…

cs.NI2021

An Efficient Multi-Link Channel Model for LiFi

Sreelal Maravanchery Mana, Kerolos Gabra Kamel Gabra, Sepideh Mohammadi Kouhini +3

In this paper, we report for the first time on a new channel modelling technique for multi-link LiFi scenarios. By considering simplified numerical calculation, it models the links…

cs.LG2021★ 8 cited

ECQ: Explainability-Driven Quantization for Low-Bit and Sparse DNNs

Daniel Becking, Maximilian Dreyer, Wojciech Samek +2

The remarkable success of deep neural networks (DNNs) in various applications is accompanied by a significant increase in network parameters and arithmetic operations. Such increas…

cs.CV2021★ 5 cited

Zero in on Shape: A Generic 2D-3D Instance Similarity Metric learned from Synthetic Data

Maciej Janik, Niklas Gard, Anna Hilsmann +1

We present a network architecture which compares RGB images and untextured 3D models by the similarity of the represented shape. Our system is optimised for zero-shot retrieval, me…

eess.IV2021★ 3 cited

A Complete End-To-End Open Source Toolchain for the Versatile Video Coding (VVC) Standard

Adam Wieckowski, Christian Lehmann, Benjamin Bross +4

Versatile Video Coding (VVC) is the most recent international video coding standard jointly developed by ITU-T and ISO/IEC, which has been finalized in July 2020. VVC allows for si…

cs.NI2021★ 28 cited

The Graph Neural Networking Challenge: A Worldwide Competition for Education in AI/ML for Networks

José Suárez-Varela, Miquel Ferriol-Galmés, Albert López +21

During the last decade, Machine Learning (ML) has increasingly become a hot topic in the field of Computer Networks and is expected to be gradually adopted for a plethora of contro…

cs.IT2021★ 1 cited

Deep Learning Beam Optimization in Millimeter-Wave Communication Systems

Rafail Ismayilov, Renato L. G. Cavalcante, Sławomir Stańczak

We propose a method that combines fixed point algorithms with a neural network to optimize jointly discrete and continuous variables in millimeter-wave communication systems, so th…

eess.SP2021★ 5 cited

Deep Learning Based Hybrid Precoding in Dual-Band Communication Systems

Rafail Ismayilov, Renato L. G. Cavalcante, Sławomir Stańczak

We propose a deep learning-based method that uses spatial and temporal information extracted from the sub-6GHz band to predict/track beams in the millimeter-wave (mmWave) band. In…

quant-ph2021★ 12 cited

Single-component gradient rules for variational quantum algorithms

Thomas Hubregtsen, Frederik Wilde, Shozab Qasim +1

Many near-term quantum computing algorithms are conceived as variational quantum algorithms, in which parameterized quantum circuits are optimized in a hybrid quantum-classical set…

quant-ph2021★ 4 cited

Encoding-dependent generalization bounds for parametrized quantum circuits

Matthias C. Caro, Elies Gil-Fuster, Johannes Jakob Meyer +2

A large body of recent work has begun to explore the potential of parametrized quantum circuits (PQCs) as machine learning models, within the framework of hybrid quantum-classical…

math.OC2021★ 2 cited

l1-Norm Minimization with Regula Falsi Type Root Finding Methods

Metin Vural, Aleksandr Y. Aravkin, Sławomir Stan'czak

Sparse level-set formulations allow practitioners to find the minimum 1-norm solution subject to likelihood constraints. Prior art requires this constraint to be convex. In this le…

cs.IT2021

Robust Cell-Load Learning with a Small Sample Set

Daniyal Amir Awan, Renato L. G. Cavalcante, Slawomir Stanczak

Learning of the cell-load in radio access networks (RANs) has to be performed within a short time period. Therefore, we propose a learning framework that is robust against uncertai…

cs.IT2021

Set-Theoretic Learning for Detection in Cell-Less C-RAN Systems

Daniyal Amir Awan, Renato L. G. Cavalcante, Zoran Utkovski +1

Cloud-radio access network (C-RAN) can enable cell-less operation by connecting distributed remote radio heads (RRHs) via fronthaul links to a powerful central unit. In conventiona…

eess.SP2021★ 189 cited

Self-supervised representation learning from 12-lead ECG data

Temesgen Mehari, Nils Strodthoff

Clinical 12-lead electrocardiography (ECG) is one of the most widely encountered kinds of biosignals. Despite the increased availability of public ECG datasets, label scarcity rema…

hep-ph2021★ 28 cited

Emergent Hadrons and Diquarks

Kenji Fukushima, Jan M. Pawlowski, Nils Strodthoff

We discuss the emergence of a low-energy effective theory with quarks, mesons, diquarks and baryons at vanishing and finite baryon density from first principle QCD. The present wor…

eess.SP2021★ 12 cited

Multi-Group Multicast Beamforming by Superiorized Projections onto Convex Sets

Jochen Fink, Renato L. G. Cavalcante, Slawomir Stanczak

In this paper, we propose an iterative algorithm to address the nonconvex multi-group multicast beamforming problem with quality-of-service constraints and per-antenna power constr…

cs.LG2021★ 11 cited

PredDiff: Explanations and Interactions from Conditional Expectations

Stefan Blücher, Johanna Vielhaben, Nils Strodthoff

PredDiff is a model-agnostic, local attribution method that is firmly rooted in probability theory. Its simple intuition is to measure prediction changes while marginalizing featur…

cs.IT2021★ 22 cited

Joint Source-Channel Coding for Semantics-Aware Grant-Free Radio Access in IoT Fog Networks

Johannes Dommel, Zoran Utkovski, Osvaldo Simeone +1

A fog-radio access network (F-RAN) architecture is studied for an Internet-of-Things (IoT) system in which wireless sensors monitor a number of multi-valued events and transmit in…

cs.CY2021★ 335 cited

Personalized Education in the AI Era: What to Expect Next?

Setareh Maghsudi, Andrew Lan, Jie Xu +1

The objective of personalized learning is to design an effective knowledge acquisition track that matches the learner's strengths and bypasses her weaknesses to ultimately meet her…

cs.IT2021★ 22 cited

Over-The-Air Computation in Correlated Channels

Matthias Frey, Igor Bjelakovic, Slawomir Stanczak

This paper addresses the problem of Over-The-Air (OTA) computation in wireless networks which has the potential to realize huge efficiency gains for instance in training of distrib…