Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
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...
A new concept for spatially resolved coherent detection with vertically illuminated photodetectors targeting ranging applications
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...
A Unifying Review of Deep and Shallow Anomaly Detection
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...
Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning
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...
Optoelectronic frequency-modulated continuous-wave terahertz spectroscopy with 4 THz bandwidth
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...
Inferring respiratory and circulatory parameters from electrical impedance tomography with deep recurrent models
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...
InP-Components for 100 Gbaud Optical Data Center Communication
Externally modulated DFB lasers (EML) and vertically illuminated photodetectors are presented. Because of their excellent high-speed behavior and operation wavelength of 1310 nm, the devices are of interest for intra-data center communication....
Robustifying Models Against Adversarial Attacks by Langevin Dynamics
This paper proposes a novel, simple yet effective defense strategy for adversarial attacks on deep learning models. Our algorithm, called MALA for DEfense (MALADE), is applicable to any existing classifier, providing robust defense as well as...
Inverse Design Strategies for Large Passive Waveguide Structures
Inverse design is rapidly gaining popularity for automated design of photonic components. Two methods to improve it for large passive waveguide structures are developed: Adaptive Threshold Binarization and Hybrid Optimization. To demonstrate...
Neural Face Models for Example-Based Visual Speech Synthesis
In this paper we present an example-based approach for visual speech synthesis. We combine the advantages of deep generative models and classical animation approaches to create a real-time capable facial animation framework based on volumetric...