Recent publications

May 2021

Predicting the Binding of SARS-CoV-2 Peptides to the Major Histocompatibility Complex with Recurrent Neural Networks

Johanna Vielhaben, Nils Strodthoff, Markus Wenzel, Eva Weicken

Predicting the binding of viral peptides to the major histocompatibility complex with machine learning can potentially extend the computational immunology toolkit for vaccine development, and serve as a key component in the fight against a pandemic. In this work, we adapt and extend USMPep, a recently proposed, conceptually simple prediction algorithm based on recurrent neural networks. Most notably, we combine regressors (binding affinity data) and classifiers (mass spectrometry data) from qualitatively different data sources to obtain a more comprehensive prediction tool. We evaluate the performance on a recently released SARS-CoV-2 dataset with binding stability measurements. USMPep not only sets new benchmarks on selected single alleles, but consistently turns out to be among the best-performing methods or, for some metrics, to be even the overall best-performing method for this task.


March 2021

A Physical Layer for Low Power Optical Wireless Communications

Malte Hinrichs, Volker Jungnickel, Ronald Freund, Jonas Hilt, Anagnostis Paraskevopoulos, Pablo Wilke Berenguer, Dominic Schulz, Peter Hellwig, Kai Lennert Bober

With the goal of enabling optical wireless communications for mobile devices, we assess a physical layer based on high-bandwidth on-off keying modulation. This allows for amplifier designs that avoid operation in a resistive mode, reducing their energy usage to a fraction. Link-level simulations show that the investigated physical layer can deal with typical frontend limitations and can operate in challenging non-line-of-sight channels.


March 2021

Example-Based Facial Animation of Virtual Reality Avatars using Auto-Regressive Neural Networks

Wolfgang Paier, Peter Eisert, Anna Hilsmann

We present a hybrid animation approach that combines example-based and neural animation methods to create a simple, yet powerful animation regime for human faces. We introduce a light-weight auto-regressive network to transform our animation-database into a parametric model. During training, our network learns the dynamics of facial expressions, which enables the replay of annotated sequences from our animation database as well as their seamless concatenation in new order.


March 2021

Radiation pattern of planar optoelectronic antennas for broadband continuous-wave terahertz emission

Simon Nellen, Martin Schell, Björn Globisch, Robert Kohlhaas, Lars Liebermeister, Milan Deumer, Sebastian Lauck, Garrit William Johannes Schwanke

We measured and simulated the radiation pattern of continuous-wave terahertz emitters between 100 and 500 GHz. We could improve the radiation pattern by optimizing the connection between terahertz source and antenna: Unwanted side lobes were reduced by more than 10 dB and the beam angle was narrowed to 9° at 300 GHz. These improvements are relevant for wireless communication links and lensless terahertz imaging.


March 2021

Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications

Wojciech Samek, Klaus-Robert Müller, Sebastian Lapuschkin, Grégoire Montavon, Christopher J. Anders

This paper provides a timely overview of the field of explainable artificial intelligence (XAI). It explains the theoretical foundations of interpretability algorithms, outlines best practice aspects, demonstrates successful usage of XAI in selected application scenarios, and discusses challenges and possible future directions of this active emerging field.


March 2021

A new concept for spatially resolved coherent detection with vertically illuminated photodetectors targeting ranging applications

Pascal Rustige, Patrick Runge, Martin Schell, Francisco M. Soares, Jan Krause

This paper proposes a novel approach for coherent detection with double-side vertically illuminated photodetectors. Signal and local oscillator are injected collinearly from opposite sides of the photodetector chip. The concept inherently provides angular selective detection and can be used for developing compact, solid-state receiver modules for coherent light detection and ranging (LiDAR).


February 2021

A Unifying Review of Deep and Shallow Anomaly Detection

Lukas Ruff, Klaus-Robert Müller, Wojciech Samek, Grégoire Montavon, Jacob R. Kauffmann, Robert A. Vandermeulen, Marius Kloft, Thomas G. Dietterich

This paper gives a comprehensive overview over classic shallow and novel deep approaches to anomaly detection. We identify the common underlying principles and provide an empirical assessment of major existing methods that are enriched by the use of recent explainability techniques. We present specific worked-through examples together with practical advice and discuss open challenges.


February 2021

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

Seul-Ki Yeom, Klaus-Robert Müller, Wojciech Samek, Alexander Binder, Sebastian Lapuschkin, Simon Wiedemann, Philipp Seegerer

This paper proposes a novel criterion for CNN pruning inspired by neural network interpretability: The most relevant units, i.e. weights or filters, are automatically found using their relevance scores obtained from concepts of explainable AI (XAI). By exploring this idea, we connect the lines of interpretability and model compression research.


February 2021

Optoelectronic frequency-modulated continuous-wave terahertz spectroscopy with 4 THz bandwidth

Lars Liebermeister, Martin Schell, Simon Nellen, Björn Globisch, Robert Kohlhaas, Steffen Breuer, Milan Deumer, Sebastian Lauck

Time-domain spectroscopy with terahertz frequencies typically requires complex and bulky systems. Here, the authors present an optoelectronics-based, frequency-domain terahertz sensing technique which offers competitive measurement performance in a much simpler system.


February 2021

Inferring respiratory and circulatory parameters from electrical impedance tomography with deep recurrent models

Nils Strodthoff, Claas Strodthoff, Tobias Becher, Inéz Frerichs, Norbert Weiler

Electrical impedance tomography (EIT) is a non-invasive imaging modality that allows a continuous assessment of changes in regional bioimpedance of different organs. One of its most common biomedical applications is monitoring regional ventilation distribution in critically ill patients treated in intensive care units. In this work, we put forward a proof-of-principle study that demonstrates how one can reconstruct synchronously measured respiratory or circulatory parameters from the EIT image sequence using a deep learning model trained in an end-to-end fashion. For this purpose, we devise an architecture with a convolutional feature extractor whose output is processed by a recurrent neural network. We demonstrate that one can accurately infer absolute volume, absolute flow, normalized airway pressure and within certain limitations even the normalized arterial blood pressure from the EIT signal alone, in a way that generalizes to unseen patients without prior calibration. As an outlook with direct clinical relevance, we furthermore demonstrate the feasibility of reconstructing the absolute transpulmonary pressure from a combination of EIT and absolute airway pressure, as a way to potentially replace the invasive measurement of esophageal pressure. With these results, we hope to stimulate further studies building on the framework put forward in this work.



Items per page10ǀ20ǀ30
Results 1-10 of 47
<< < 1 2 3 4 5 > >>