58 citations · 237 across the 39 of their papers we have counts for
44 papers
Compression Through Time: An Interplay of Separability, Stationarity and Capacity
Nikolaus Kopp, Franz Pernkopf, Bernhard Geiger
Information-theoretic and geometric compression have been widely studied as possible explanations for generalization. Yet their temporal dynamics in recurrent networks remain large…
Adaptive Variational Inference in Probabilistic Graphical Models: Beyond Bethe, Tree-Reweighted, and Convex Free Energies
Harald Leisenberger, Franz Pernkopf
Variational inference in probabilistic graphical models aims to approximate fundamental quantities such as marginal distributions and the partition function. Popular approaches are…
Function Space Diversity for Uncertainty Prediction via Repulsive Last-Layer Ensembles
Sophie Steger, Christian Knoll, Bernhard Klein +2
Bayesian inference in function space has gained attention due to its robustness against overparameterization in neural networks. However, approximating the infinite-dimensional fun…
On the Convexity and Reliability of the Bethe Free Energy Approximation
Harald Leisenberger, Christian Knoll, Franz Pernkopf
The Bethe free energy approximation provides an effective way for relaxing NP-hard problems of probabilistic inference. However, its accuracy depends on the model parameters and pa…
Effective Bayesian Causal Inference via Structural Marginalisation and Autoregressive Orders
Christian Toth, Christian Knoll, Franz Pernkopf +1
The traditional two-stage approach to causal inference first identifies a single causal model (or equivalence class of models), which is then used to answer causal queries. However…
Angle-Equivariant Convolutional Neural Networks for Interference Mitigation in Automotive Radar
Christian Oswald, Mate Toth, Paul Meissner +1
In automotive applications, frequency modulated continuous wave (FMCW) radar is an established technology to determine the distance, velocity and angle of objects in the vicinity o…
"UWBCarGraz" Dataset for Car Occupancy Detection using Ultra-Wideband Radar
Jakob Möderl, Stefan Posch, Franz Pernkopf +1
We present a data-driven car occupancy detection algorithm using ultra-wideband radar based on the ResNet architecture. The algorithm is trained on a dataset of channel impulse res…
Fast Variational Block-Sparse Bayesian Learning
Jakob Möderl, Erik Leitinger, Bernard H. Fleury +2
We propose a variational Bayesian (VB) implementation of block-sparse Bayesian learning (BSBL) to compute proxy probability density functions (PDFs) that approximate the posterior…
Self-attention for Enhanced OAMP Detection in MIMO Systems
Alexander Fuchs, Christian Knoll, Nima N. Moghadam +3
Multiple-Input Multiple-Output (MIMO) systems are essential for wireless communications. Sinceclassical algorithms for symbol detection in MIMO setups require large computational r…
Variational Inference of Structured Line Spectra Exploiting Group-Sparsity
Jakob Möderl, Franz Pernkopf, Klaus Witrisal +1
In this paper, we present a variational inference algorithm that decomposes a signal into multiple groups of related spectral lines. The spectral lines in each group are associated…
Variational Message Passing-Based Respiratory Motion Estimation and Detection Using Radar Signals
Jakob Möderl, Erik Leitinger, Franz Pernkopf +1
We present a variational message passing (VMP) approach to detect the presence of a person based on their respiratory chest motion using multistatic ultra-wideband (UWB) radar. In…
Active Bayesian Causal Inference
Christian Toth, Lars Lorch, Christian Knoll +4
Causal discovery and causal reasoning are classically treated as separate and consecutive tasks: one first infers the causal graph, and then uses it to estimate causal effects of i…
Explainable Machine Learning for Breakdown Prediction in High Gradient RF Cavities
Christoph Obermair, Thomas Cartier-Michaud, Andrea Apollonio +10
The occurrence of vacuum arcs or radio frequency (rf) breakdowns is one of the most prevalent factors limiting the high-gradient performance of normal conducting rf cavities in par…
Resource-efficient Deep Neural Networks for Automotive Radar Interference Mitigation
Johanna Rock, Wolfgang Roth, Mate Toth +2
Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous vehicles. With a rising number of radar sensors and the so far unregulated a…
Distribution Mismatch Correction for Improved Robustness in Deep Neural Networks
Alexander Fuchs, Christian Knoll, Franz Pernkopf
Deep neural networks rely heavily on normalization methods to improve their performance and learning behavior. Although normalization methods spurred the development of increasingl…
Lung Sound Classification Using Co-tuning and Stochastic Normalization
Truc Nguyen, Franz Pernkopf
In this paper, we use pre-trained ResNet models as backbone architectures for classification of adventitious lung sounds and respiratory diseases. The knowledge of the pre-trained…
Crackle Detection In Lung Sounds Using Transfer Learning And Multi-Input Convolitional Neural Networks
Truc Nguyen, Franz Pernkopf
Large annotated lung sound databases are publicly available and might be used to train algorithms for diagnosis systems. However, it might be a challenge to develop a well-performi…
Complex-valued Convolutional Neural Networks for Enhanced Radar Signal Denoising and Interference Mitigation
Alexander Fuchs, Johanna Rock, Mate Toth +2
Autonomous driving highly depends on capable sensors to perceive the environment and to deliver reliable information to the vehicles' control systems. To increase its robustness, a…
End-to-end Keyword Spotting using Neural Architecture Search and Quantization
David Peter, Wolfgang Roth, Franz Pernkopf
This paper introduces neural architecture search (NAS) for the automatic discovery of end-to-end keyword spotting (KWS) models in limited resource environments. We employ a differe…
Blind Speech Separation and Dereverberation using Neural Beamforming
Lukas Pfeifenberger, Franz Pernkopf
In this paper, we present the Blind Speech Separation and Dereverberation (BSSD) network, which performs simultaneous speaker separation, dereverberation and speaker identification…
Resource-efficient DNNs for Keyword Spotting using Neural Architecture Search and Quantization
David Peter, Wolfgang Roth, Franz Pernkopf
This paper introduces neural architecture search (NAS) for the automatic discovery of small models for keyword spotting (KWS) in limited resource environments. We employ a differen…
Deep Interference Mitigation and Denoising of Real-World FMCW Radar Signals
Johanna Rock, Mate Toth, Paul Meissner +1
Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous cars. Key performance factors are a fine range resolution and the possibilit…
Quantized Neural Networks for Radar Interference Mitigation
Johanna Rock, Wolfgang Roth, Paul Meissner +1
Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous vehicles. Key performance factors are weather resistance and the possibility…
On Resource-Efficient Bayesian Network Classifiers and Deep Neural Networks
Wolfgang Roth, Günther Schindler, Holger Fröning +1
We present two methods to reduce the complexity of Bayesian network (BN) classifiers. First, we introduce quantization-aware training using the straight-through gradient estimator…