Aktuelle Publikationen

Januar 2023

Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond

Anna Hedström, Wojciech Samek, Sebastian Lapuschkin, Leander Weber, Dilyara Bareeva, Franz Motzkus, Marina M.-C. Höhne, Daniel Krakowczyk

Explainability is supposed to strengthen trust in artificial intelligence, it is necessary to systematically review and compare explanation methods in order to confirm their correctness. We therefore built Quantus—a comprehensive, evaluation...


Januar 2023

Enabling Optical Modulation Format Identification Using an Integrated Photonic Reservoir and a Digital Multiclass Classifier

Guillermo von Hünefeld, Colja Schubert, Ronald Freund, Isaac Sackey, Gregor Ronniger, Johannes K. Fischer, Pooyan Safari, Rijil Thomas, Enes Seker, Piotr Cegielski, Stephan Suckow, Max Lemme, David Stahl, Sarah Masaad, Emmanuel Gooskens, Peter Bienstman

We numerically show modulation format identification in the optical domain using Silicon-on-Insulator-based Photonic-Integrated-Circuit (PIC) reservoir. Identification of 32 GBd single-polarization signals of OOK, PAM4, BPSK and QPSK is...


Januar 2023

Investigating the Performance and Suitability of Neural Network Architectures for Nonlinearity Mitigation of Optical Signals

Vegenshanti Valerian Dsilva, Colja Schubert, Ronald Freund, Isaac Sackey, Gregor Ronniger, Guillermo von Hünefeld, Binoy Chacko

We compare three different neural network architectures for nonlinearity mitigation of 32 GBd OOK and QPSK signals after transmission over a dispersion-compensated link of 10-km SSMF and 10-km DCF. OSNR gains up to 2.2 dB were achieved using...


Januar 2023

Experimental Study of In-line Nonlinearity Mitigation for a 400 Gb/s Dual-Carrier Superchannel with Joint Reception Using a Waveband-Shift-Free OPC

Isaac Sackey, Colja Schubert, Carsten Schmidt-Langhorst, Ronald Freund, Robert Elschner, Tomoyuki Kato, Takeshi Hoshida, Gregor Ronniger

We experimentally study waveband-shift-free optical phase conjugation (OPC) of a 400-Gb/s dual-carrier superchannel and discuss the effectiveness of the OPC for multi-channel nonlinear mitigation. After joint reception of the 31.44 GBd-PDM-16QAM...


Januar 2023

Ultra-Wideband All-optical Interband Wavelength Conversion Using a Low-complexity Dispersion-engineered SOI Waveguide

Isaac Sackey, Colja Schubert, Carsten Schmidt-Langhorst, Ronald Freund, Robert Elschner, Tomoyuki Kato, Takeshi Hoshida, Gregor Ronniger, Hidenobu Muranaka, Shun Okada, Yu Tanaka, Tsuyoshi Yamamoto, Md Mahasin KhanIsaac Sackey, Colja Schubert, Carsten Schmidt-Langhorst, Ronald Freund, Robert Elschner, Tomoyuki Kato, Takeshi Hoshida, Gregor Ronniger, Hidenobu Muranaka, Shun Okada, Yu Tanaka, Tsuyoshi Yamamoto, Md Mahasin Khan

We experimentally present a low-complexity dispersion-engineered all-optical wavelength-converter using a photonic integrated-circuit based on SOI waveguide. We achieve a single-sided conversion bandwidth of ~35 nm from C- to S-band, and...


Dezember 2022

Increasing the reach of visible light communication links through constant-envelope OFDM signals

Higor Camporez, Volker Jungnickel, Ronald Freund, Anagnostis Paraskevopoulos, Malte Hinrichs, Wesley Da Silva Costa, Maria Pontes, Marcelo Segatto, Helder Rocha, Jair Silva

We demonstrate the transmission of constant-envelope orthogonal frequency division multiplexing (CE-OFDM) signals, based on electrical phase modulation, in a visible light communication (VLC) system. An increased tolerance to nonlinearity...


Dezember 2022

A Novel Approach for Joint Analytical and ML-assisted GSNR Estimation in Flexible Optical Network

Farhad Arpanaei, Johannes K. Fischer, Mohammad Behnam Shariati, Pooyan Safari, Mahdi Ranjbar Zefreh, José Alberto Hernández, Andrea Carena, David Larrabeiti

We propose a novel approach to perform QoT estimation relying on joint exploitation of machine learning and analytical formula that offers accurate estimation when applied to scenarios with heterogeneous span profiles and sparsely occupied links....


Dezember 2022

Automated Dataset Generation for QoT Estimation in Coherent Optical Communication Systems

Caio Marciano Santos, Colja Schubert, Carsten Schmidt-Langhorst, Robert Emmerich, Johannes K. Fischer, Mohammad Behnam Shariati

We demonstrate sophisticated laboratory automation and data pipeline capable of generating large, diverse, and high-quality public datasets. The demo covers the full workflow from setup reconfiguration to data monitoring and storage, represented...


Dezember 2022

Demonstration of a Real-Time ML Pipeline for Traffic Forecasting in AI-Assisted F5G Optical Access Networks

Mihail Balanici, Ronald Freund, Johannes K. Fischer, Mohammad Behnam Shariati, Pooyan Safari, Geronimo Bergk

We showcase a proof-of-concept demonstration of a ML pipeline for real-time traffic forecasting deployed on a passive optical access network using an XGS-PON compatible telemetry framework. The demonstration reveals the benefits of fine-granular...


Dezember 2022

Reducing Overhead for Low-Power Optical Wireless Communications

Malte Hinrichs, Volker Jungnickel, Peter Hellwig, Benjamin Poddig

We demonstrate on-off-keying optical wireless transmissions according to the IEEE P802.15.13 PM-PHY, in which we replace 8b10b line-coding by guided and non-guided data scramblers and compensate the remaining high-pass distortions through a...


Dezember 2022

Demonstration of 1.75 Gbit/s VCSEL-Based Non-Directed Optical Wireless Communications With OOK and FDE

Malte Hinrichs, Volker Jungnickel, Martin Schubert, Wen Xu, Ronald Freund, Christoph Kottke, Dominic Schulz, Peter Hellwig, Ronald Böhnke, Giulio Boniello

We evaluate a high power on-off-keying transmitter for non-directed optical wireless communications based on VCSEL-arrays. Error-free transmission after FEC with a net data rate of 1.75 GBit/s is achieved across a distance of 2.5 m with a...


Dezember 2022

Toward AI-enhanced VLC Systems for Industrial Applications

Wesley Da Silva Costa, Volker Jungnickel, Ronald Freund, Anagnostis Paraskevopoulos, Malte Hinrichs, Higor Camporez, Maria Pontes, Marcelo Segatto, Helder Rocha, Jair Silva

This paper presents optimization and deep learning procedures aiming at increasing power and spectral efficiency of visible light communications systems for two exemplary industrial scenarios. We propose a hybrid multi-objective optimization to...


Dezember 2022

Comparison of Uni- and Multimodal Interfaces for Spatial Interaction

David Przewozny, Sebastian Bosse, Detlef Runde, Paul Chojecki, Niklas Gard, Niklas Hoerner

Multimodal user interfaces can provide better solutions, as they combine various interaction modalities to enable more flexibility and naturalness in human-machine interactions (HMI). They allow to seamlessly adapt to user and application...


Dezember 2022

Explaining the Decisions of Convolutional and Recurrent Neural Networks

Wojciech Samek, Klaus-Robert Müller, Leila Arras, Grégoire Montavon, Ahmed Osman

In this chapter we discuss the algorithmic and theoretical underpinnings of layer-wise relevance propagation (LRP), apply the method to a complex model trained for the task of visual question answering (VQA), and demonstrate that it produces...


Dezember 2022

Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement

Leander Weber, Wojciech Samek, Alexander Binder, Sebastian Lapuschkin

Explainable Artificial Intelligence (XAI) is an emerging research field bringing transparency to highly complex and opaque machine learning (ML) models. This paper offers a comprehensive overview over techniques that apply XAI practically to...


November 2022

150 GBd PAM-4 Electrical Signal Generation using SiGe-Based Analog Multiplexer Ic

Jonathan Schostak, Volker Jungnickel, Ronald Freund, Tobias Tannert, Markus Grözing, Manfred Berroth, Christian Schmidt, Holger Rücker

Analog Multiplexers in Silicon-Germanium technology allow increasing the analog bandwidth of Digital-to-Analog-Converters and enable faster data transfers. We demonstrated 4-level pulse-amplitude modulation (PAM-4) signal transmission at 150 GBd...


November 2022

Towards the Interpretability of Deep Learning Models for Multi-Modal Neuroimaging: Finding Structural Changes of the Ageing Brain

Simon M. Hofmann, Klaus-Robert Müller, Wojciech Samek, Arno Villringer, Sebastian Lapuschkin, Frauke Beyer, Markus Loeffler, A. Veronica Witte, Ole Goltermann

Brain-age (BA) estimates based on deep learning are increasingly used as neuroimaging biomarker for brain health; however, the underlying neural features have remained unclear. We combined ensembles of convolutional neural networks with...


November 2022

New Definitions of Human Lymphoid and Follicular Cell Entities in Lymphatic Tissue by Machine Learning

Patrick Wagner, Klaus-Robert Müller, Wojciech Samek, Frederick Klauschen, Arturo Marban, Nils Strodthoff, Philipp Seegerer, Patrick Wurzel, Sonja Scharf, Hendrik Schäfer, Andreas Loth, Sylvia Hartmann, Martin-Leo Hansmann

Histological sections of the lymphatic system are usually the basis of static (2D) morphological investigations. Here, we performed a dynamic (4D) analysis of human reactive lymphoid tissue using confocal fluorescent laser microscopy in...


Oktober 2022

Time Adaptive Probabilistic Shaping for Combined Optical/THz Links

In-Ho Baek, Colja Schubert, Ronald Freund, Robert Elschner, Frederik Bart, Fred Meier, David Hellmann, Andreas Maaßen

We investigate the applicability of PAS for outdoor THz wireless links in simulations with weather-dependent loss models. Link performances are evaluated and optimal shaping entropies are determined to adjust error rates to a given FEC threshold....


Oktober 2022

Edge Cloud based Visual Inspection for Automatic Quality Assurance in Production

Pooyan Safari, David Przewozny, Paul Chojecki, Ronald Freund, Johannes K. Fischer, Mohammad Behnam Shariati, Axel Vick, Moritz Chemnitz

We present a remote quality assurance use-case in distributed production sites that can be realized with the powerful capabilities of Artificial Intelligence (AI) combined with real-time video streaming systems and high-speed, low-latency...


Oktober 2022

Ultra-Broadband Optical Wavelength-Conversion using Nonlinear Multi-Modal Optical Waveguides

Norbert Hanik, Colja Schubert, Ronald Freund, Lars Zimmermann, Isaac Sackey, Gregor Ronniger, Tasnad Kernetzky, Yizhao Jia, Ulrike Höfler

Ultra-Broadband Wavelength Conversion is one of the key issues of future optical networks. The physical background of ultra-broadband optical wavelength conversion in a multi-modal Silicon waveguide and methods to optimize its functionality are...


Oktober 2022

Fixed 5th Generation Advanced and Beyond

F. J. Effenberger, D. Hillerkuss, I. Tomkos, Johannes K. Fischer, Mohammad Behnam Shariati, F. J. Effenberger, Yike Jiang, Thierno Diallo, Zhuotong Li, Wenhong Liu, Weizhao Yu, Yongli Zhao, Li Ao, Xiaobo Cao Cao, Qian Liu, Ming Jiang, Jialiang Jin, Junjie Li, Jian Tang, Anxu Zhang, Chengliang Zhang, Dezhi Zhang, Shikui Shen, Yue Sun, Xiongyan Tang, Guangquan Wang, Yuguang Chang, Raul Muñoz, Manny R. Estrada, Jorge Bonifacio, Marcus Brunner, Francis Keshmiri, Hongyu Li, Yi Lin, Xiang Liu, Frank Melinn, Jun Zhou, Qidong Zou, Steven Hill, Lloyd Mphahlele, Evandro Bender, Philippe Chanclou, Gaël Simon, Olivier Ferveur, Luca Pesando, Sandesh Manganahalli Jayaprakash, Marcel van Sambeek, Teun van der Veen, Oguzkagan Kanlidere

One of the overarching goals of the ETSI Industry Specification Group (ISG) F5G on Fifth Generation Fixed Network is to establish a regular rhythm of evolution for the fixed telecommunications network. So far, F5G has published technical...


Oktober 2022

Towards Trustworthy AI in Dentistry

Jackie Ma, Wojciech Samek, Sebastian Lapuschkin, Falk Schwendicke, Joachim Krois, Lisa Schneider, Reduan Achtibat, Martha Duchrau

Medical and dental artificial intelligence (AI) require the trust of both users and recipients of the AI to enhance implementation, acceptability, reach, and maintenance. Standardization is one strategy to generate such trust, with quality...


Oktober 2022

Federated Learning in Dentistry: Chances and Challenges

Roman Rischke, Karsten Müller, Wojciech Samek, Falk Schwendicke, Joachim Krois, Lisa Schneider

Building performant and robust artificial intelligence (AI)–based applications for dentistry requires large and high-quality data sets. Collaborative efforts are limited as privacy constraints forbid direct sharing across the borders of these...


Oktober 2022

Measurably Stronger Explanation Reliability Via Model Canonization

Franz Motzkus, Sebastian Lapuschkin, Leander Weber

Network canonization has recently been introduced, restructuring a neural network model into a functionally identical equivalent to which established explanation methods can be applied optimally. In this work, we quantitatively verify the...


Oktober 2022

Optical Generation and Transmission of mmWave Signals in 5G ERA: Experimental Evaluation Paradigm

Efstathios Andrianopoulos, Christos Kouloumentas, Norbert Keil, David de Felipe Mesquida, Simon Nellen, Panos Groumas, Lefteris Gounaridis, Christos Tsokos, Tianwen Qian, Herkules Avramopoulos, Adam Raptakis, Nikolaos K. Lyras

We demonstrate the generation, of a mmWave signal via the injection of an optical frequency comb (OFC) into an integrated tunable dual distributed Bragg reflector (DBR) laser as well as the fiber transmission and the processing of this signal by...


Oktober 2022

To Pretrain or Not? A Systematic Analysis of the Benefits of Pretraining in Diabetic Retinopathy

Vignesh Srinivasan, Klaus-Robert Müller, Wojciech Samek, Alexander Binder, Nils Strodthoff, Jackie Ma

In this work, we aim to understand what type of pretraining works reliably in practice and what type of pretraining dataset is best suited to achieve good performance in small target dataset size scenarios. Considering diabetic retinopathy...


Oktober 2022

History Dependent Significance Coding for Incremental Neural Network Compression

Gerhard Tech, Karsten Müller, Thomas Wiegand, Detlev Marpe, Heiko Schwarz, Heiner Kirchhoffer, Wojciech Samek, Jonathan Pfaff, Paul Haase, Daniel Becking

This paper presents an improved probability estimation scheme for the entropy coder of Incremental Neural Network Coding (INNC), which is currently under standardization in ISO/IEC MPEG. Major finding is that the probability of a significant...


Oktober 2022

Ultrawideband Systems and Networks: Beyond C+L -Band

Takeshi Hoshida, Johannes Fischer, Tomoyuki Kato, Vittorio Curri, Wladek Forysiak, Lidia Galdino, David T. Neilson, Pierluigi Poggiolini

In the evolution of optical networks, enhancement of spectral efficiency (SE) enhancement has been the most cost-efficient and thus the main driver for capacity enhancementincrease for decades. As a result, the development of optical transport...


Oktober 2022

Hyperspectral Demosaicing of Snapshot Camera Images Using Deep Learning

Eric Wisotzky, Peter Eisert, Anna Hilsmann, Charul Daudkhane

This work proposes a parallel neural network based demosaicing procedure for single-camera-one-shot-for hyperspectral imaging trained on a new ground truth dataset captured in a controlled environment by a hyperspectral snapshot camera with a 4×4...



Ergebnisse pro Seite10ǀ20ǀ30
Ergebnisse 1-30 von 164
<< < 1 2 3 4 5 6 > >>