Intelligent Systems
An intelligent system is able to perceive, learn, reason, and act in a prudent way. This involves various perception modalities such as input from cameras, microphones, sonar and other more exotic sensors. Furthermore, machine learning and pattern recognition techniques are important ingredients for reasoning under uncertainty in intelligent systems. One major aim is to extract relevant information from massive data in a semi-automatic fashion using computational and statistical methods. This interdisciplinary research is related to many fields throughout science and engineering, i.e., statistics, probability, and graph theory, optimization methods, logic, speech and image processing, control theory etcetera. The focus is on providing solutions for tasks where some kind of intelligence is inevitably essential. Application areas include bioinformatics, computer vision, natural language processing, speech processing, man-machine interfaces, expert systems, and robotics amongst others.
- Philipp Hermüller: Automated Anomaly Classification for the Post-Mortem System using Machine Learning
- Christian Toth: Bayesian Causal Inference in the Presence of Structural Uncertainty
- Martin Hofmann-Wellenhof: Physics-informed Machine Learning
- Jixiang Lei: Robust Test-Time Adaptation for Visual and Multimodal Learning under Distribution Shifts
- Sophie Steger: Uncertainty Estimation in Deep Learning and Industrial Applications
- Benedikt Mayrhofer: Voice conversion for Dysphonic and Electrolaryngeal Speech
Finished PhD Theses:
- 2025: Analysis of Message Passing Algorithms and Free Energy Approximations in Probabilistic Graphical Models — Harald Leisenberger
- 2024: Using UWB Radar to Detect Life Presence Inside a Vehicle — Jakob Möderl
- 2023: Interpretable Fault Prediction for CERN Energy Frontier Colliders — Christoph Obermair
- 2022: Deep Learning for Resource-Constrained Radar Systems — Johanna Rock
- 2022: Robust Lung Sound and Acoustic Scene Classification — Truc Nguyen
- 2021: Towards the Evolution of Neural Acoustic Beamformers — Lukas Pfeifenberger
- 2019: Speech Enhancement Using Deep Neural Beamformers — Matthias Zöhrer
- 2013: Kernel PCA and Pre-Image Iterations for Speech Enhancemen — Christina Leitner
- 2012: Probabilistic Model-Based Multiple Pitch Tracking of Speech — Michael Wohlmayr
- 2010: Phonetic Similarity Matching of Non-Literal Transcripts in Automatic Speech Recognition — Stefan Petrik
- : Probabilistic Methods for Resource Efficiency in Machine Learning — Wolfgang Roth
- : Understanding the Behavior of Belief Propagation — Christian Knoll
- : Maximum Margin Bayesian Networks — Sebastian Tschiatschek
- : Improving Efficiency and Generalization in Deep Learning Models for Industrial Applications — Alex Fuchs
- : Foundations of Sum-Product Networks for Probabilistic Modeling — Robert Peharz
- : Distributed Sparse Bayesian Regression in Wireless Sensor Networks — Thomas Buchgraber
- : Sum-Product Networks for Complex Modelling Scenarios — Martin Trapp
- : A Holistic Approach to Multi-channel Lung Sound Classification — Elmar Messner