no code implementations • 22 Feb 2024 • Christian Toth, Christian Knoll, Franz Pernkopf, Robert Peharz
Specifically, we decompose the problem of inferring the causal structure into (i) inferring a topological order over variables and (ii) inferring the parent sets for each variable.
no code implementations • 18 Dec 2023 • Christian Oswald, Mate Toth, Paul Meissner, Franz Pernkopf
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 of the vehicle.
no code implementations • 15 Dec 2023 • Christian Oswald, Mate Toth, Paul Meissner, Franz Pernkopf
In this paper we propose a new method for training neural networks (NNs) for frequency modulated continuous wave (FMCW) radar mutual interference mitigation.
no code implementations • 17 Nov 2023 • Jakob Möderl, Stefan Posch, Franz Pernkopf, Klaus Witrisal
Our presented ResNet architecture is able to outperform the VMP algorithm in terms of the area under the receiver operating curve (AUC) at low signal-to-noise ratios (SNRs) for all three activity levels of the target.
1 code implementation • 1 Jun 2023 • Jakob Möderl, Franz Pernkopf, Klaus Witrisal, Erik Leitinger
We present a fast update rule for variational block-sparse Bayesian learning (SBL) methods.
no code implementations • 6 Mar 2023 • Jakob Möderl, Franz Pernkopf, Klaus Witrisal, Erik Leitinger
The spectral lines in each group are associated with a group parameter common to all spectral lines within the group.
no code implementations • 14 Oct 2022 • Jakob Möderl, Erik Leitinger, Franz Pernkopf, Klaus Witrisal
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.
1 code implementation • 4 Jun 2022 • Christian Toth, Lars Lorch, Christian Knoll, Andreas Krause, Franz Pernkopf, Robert Peharz, Julius von Kügelgen
In this work, we propose Active Bayesian Causal Inference (ABCI), a fully-Bayesian active learning framework for integrated causal discovery and reasoning, which jointly infers a posterior over causal models and queries of interest.
1 code implementation • 10 Feb 2022 • Christoph Obermair, Thomas Cartier-Michaud, Andrea Apollonio, William Millar, Lukas Felsberger, Lorenz Fischl, Holger Severin Bovbjerg, Daniel Wollmann, Walter Wuensch, Nuria Catalan-Lasheras, Marçà Boronat, Franz Pernkopf, Graeme Burt
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 particle accelerators.
BIG-bench Machine Learning Explainable artificial intelligence +1
no code implementations • 25 Jan 2022 • Johanna Rock, Wolfgang Roth, Mate Toth, Paul Meissner, Franz Pernkopf
We analyze the quantization of (i) weights and (ii) activations of different CNN-based model architectures.
no code implementations • 5 Oct 2021 • Alexander Fuchs, Christian Knoll, Franz Pernkopf
The most common normalization method, batch normalization, reduces the distribution shift during training but is agnostic to changes in the input distribution during test time.
1 code implementation • Interspeech 2021 • Lukas Pfeifenberger, Matthias Zoehrer, Franz Pernkopf
This paper proposes the Cross-Domain Echo-Controller(CDEC), submitted to the Interspeech 2021 AEC-Challenge. The algorithm consists of three building blocks: (i) a Time-Delay Compensation (TDC) module, (ii) a frequency-domainblock-based Acoustic Echo Canceler (AEC), and (iii) a Time-Domain Neural-Network (TD-NN) used as a post-processor. Our system achieves an overall MOS score of 3. 80, while onlyusing 2. 1 million parameters at a system latency of 32ms.
no code implementations • 4 Aug 2021 • 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.
Ranked #6 on Audio Classification on ICBHI Respiratory Sound Database (using extra training data)
no code implementations • 30 Apr 2021 • Truc Nguyen, Franz Pernkopf
In this paper, we use transfer learning to tackle the mismatch of the recording setup.
no code implementations • 29 Apr 2021 • Alexander Fuchs, Johanna Rock, Mate Toth, Paul Meissner, Franz Pernkopf
Our experiments show, that the use of CVCNNs increases data efficiency, speeds up network training and substantially improves the conservation of phase information during interference removal.
no code implementations • 14 Apr 2021 • 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.
Ranked #15 on Keyword Spotting on Google Speech Commands (Google Speech Commands V2 12 metric)
1 code implementation • 24 Mar 2021 • 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 in a single neural network.
2 code implementations • 18 Dec 2020 • 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.
no code implementations • 4 Dec 2020 • Johanna Rock, Mate Toth, Paul Meissner, Franz Pernkopf
We combine real measurements with simulated interference in order to create input-output data suitable for training the model.
no code implementations • 25 Nov 2020 • Johanna Rock, Wolfgang Roth, Paul Meissner, Franz Pernkopf
Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous vehicles.
1 code implementation • Interspeech 2020 • Lukas Pfeifenberger, Franz Pernkopf
The acoustic front-end of hands-free communication de-vices introduces a variety of distortions to the linear echo pathbetween the loudspeaker and the microphone.
1 code implementation • 22 Oct 2020 • Wolfgang Roth, Günther Schindler, Holger Fröning, Franz Pernkopf
We present two methods to reduce the complexity of Bayesian network (BN) classifiers.
1 code implementation • 21 Aug 2020 • Wolfgang Roth, Franz Pernkopf
Learning the structure of Bayesian networks is a difficult combinatorial optimization problem.
no code implementations • 22 Jul 2020 • Lukas Pfeifenberger, Matthias Zöhrer, Günther Schindler, Wolfgang Roth, Holger Fröning, Franz Pernkopf
While machine learning techniques are traditionally resource intensive, we are currently witnessing an increased interest in hardware and energy efficient approaches.
no code implementations • 22 Jul 2020 • Alexander Fuchs, Franz Pernkopf
Capsule networks offer interesting properties and provide an alternative to today's deep neural network architectures.
no code implementations • 7 Jan 2020 • Wolfgang Roth, Günther Schindler, Bernhard Klein, Robert Peharz, Sebastian Tschiatschek, Holger Fröning, Franz Pernkopf, Zoubin Ghahramani
While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-efficient approaches.
no code implementations • pproximateinference AABI Symposium 2019 • Philipp Gabler, Martin Trapp, Hong Ge, Franz Pernkopf
Many modern machine learning algorithms, such as automatic differentiation (AD) and versions of approximate Bayesian inference, can be understood as a particular case of message passing on some computation graph.
1 code implementation • 10 Oct 2019 • Martin Trapp, Robert Peharz, Franz Pernkopf, Carl E. Rasmussen
Gaussian Processes (GPs) are powerful non-parametric Bayesian regression models that allow exact posterior inference, but exhibit high computational and memory costs.
no code implementations • 10 Jul 2019 • Bernhard K. Aichernig, Roderick Bloem, Masoud Ebrahimi, Martin Horn, Franz Pernkopf, Wolfgang Roth, Astrid Rupp, Martin Tappler, Markus Tranninger
Therefore, there is considerable interest in learning such hybrid behavior by means of machine learning which requires sufficient and representative training data covering the behavior of the physical system adequately.
1 code implementation • 24 Jun 2019 • Johanna Rock, Mate Toth, Elmar Messner, Paul Meissner, Franz Pernkopf
Driver assistance systems as well as autonomous cars have to rely on sensors to perceive their environment.
no code implementations • 12 Jun 2019 • Guenther Schindler, Wolfgang Roth, Franz Pernkopf, Holger Froening
As a result, PSP maintains prediction performance, creates a substantial amount of sparsity that is structured and, thus, easy and efficient to map to a variety of massively parallel processors, which are mandatory for utmost compute power and energy efficiency.
1 code implementation • NeurIPS 2019 • Martin Trapp, Robert Peharz, Hong Ge, Franz Pernkopf, Zoubin Ghahramani
While parameter learning in SPNs is well developed, structure learning leaves something to be desired: Even though there is a plethora of SPN structure learners, most of them are somewhat ad-hoc and based on intuition rather than a clear learning principle.
1 code implementation • 20 May 2019 • Martin Trapp, Robert Peharz, Franz Pernkopf
It seems to be a pearl of conventional wisdom that parameter learning in deep sum-product networks is surprisingly fast compared to shallow mixture models.
no code implementations • ICLR 2019 • Günther Schindler, Wolfgang Roth, Franz Pernkopf, Holger Fröning
In this work we propose a method for weight and activation quantization that is scalable in terms of quantization levels (n-ary representations) and easy to compute while maintaining the performance close to full-precision CNNs.
no code implementations • 5 Dec 2018 • Franz Pernkopf, Wolfgang Roth, Matthias Zoehrer, Lukas Pfeifenberger, Guenther Schindler, Holger Froening, Sebastian Tschiatschek, Robert Peharz, Matthew Mattina, Zoubin Ghahramani
In that way, we provide an extensive overview of the current state-of-the-art of robust and efficient machine learning for real-world systems.
no code implementations • 4 Dec 2018 • Christian Knoll, Adrian Weller, Franz Pernkopf
Belief propagation (BP) is a popular method for performing probabilistic inference on graphical models.
1 code implementation • 12 Sep 2018 • Martin Trapp, Robert Peharz, Carl E. Rasmussen, Franz Pernkopf
In this paper, we introduce a natural and expressive way to tackle these problems, by incorporating GPs in sum-product networks (SPNs), a recently proposed tractable probabilistic model allowing exact and efficient inference.
no code implementations • 6 Jul 2018 • Martin Ratajczak, Sebastian Tschiatschek, Franz Pernkopf
We consider higher-order linear-chain conditional random fields (HO-LC-CRFs) for sequence modelling, and use sum-product networks (SPNs) for representing higher-order input- and output-dependent factors.
Optical Character Recognition Optical Character Recognition (OCR)
no code implementations • 4 Jun 2018 • Tobias Schrank, Franz Pernkopf
Abstraction is a fundamental part when learning behavioral models of systems.
no code implementations • ICLR 2018 • Wolfgang Roth, Franz Pernkopf
The increasing demand for neural networks (NNs) being employed on embedded devices has led to plenty of research investigating methods for training low precision NNs.
1 code implementation • 10 Oct 2017 • Martin Trapp, Tamas Madl, Robert Peharz, Franz Pernkopf, Robert Trappl
In several domains obtaining class annotations is expensive while at the same time unlabelled data are abundant.
no code implementations • 20 May 2016 • Christian Knoll, Franz Pernkopf, Dhagash Mehta, Tianran Chen
Moreover, we show that this fixed point gives a good approximation, and the NPHC method is able to obtain this fixed point.
no code implementations • 22 Jan 2016 • Robert Peharz, Robert Gens, Franz Pernkopf, Pedro Domingos
We discuss conditional independencies in augmented SPNs, formally establish the probabilistic interpretation of the sum-weights and give an interpretation of augmented SPNs as Bayesian networks.
no code implementations • NeurIPS 2014 • Matthias Zöhrer, Franz Pernkopf
We extend generative stochastic networks to supervised learning of representations.