Machine Learning and Artificial Intelligence at RUB

The ever growing machine learning and artificial intelligence research done at the Ruhr-University Bochum provides excellent opportunities for interested academics and industry partners alike. Since RUB researchers from a broad range of disciplines contribute to both fields, ml-ai.rub.de serves as an up-to-date register for core groups, study programs and projects.

Faculty of Computer Science & Institute for Neural Computation

  • Algorithms
  • Applications

The Chair of Software Engineering combines foundational and applied research to automate software engineering for the next generation of intelligent, autonomous, and variant-rich software systems. Our main application domains are automotive systems, systems software (e.g., Linux kernel), software ecosystems (e.g., Android apps), and mobile robots. We especially contribute methods and tools for AI Engineering. Software engineering supports building intelligent systems (SE4AI), as well as AI supports software engineering (AI4SE). We contribute in both areas: in SE4AI advancing the management (e.g., version/variant/experiment management) of machine-learning assets (e.g., models) and improving the empirical understanding of AI-enabled software systems; as well as in AI4SE we leverage machine-learning techniques to build novel quality assurance tools (e.g., defect prediction of software) and tools for building variant-rich systems (e.g., AI-based recommender systems).

  • Cognitive modeling

My group studies the neural and cognitive mechanisms of episodic memory and spatial navigation. We employ neural network models, abstract cognitive models, and robotics for modeling and, in collaboration with experimental labs, apply advanced data analysis methods.

  • Algorithms
  • Theory

In a broad perspective, my main research ambition is to understand the fundamental computational principles of learning that characterize intelligence. More specifically, my research interests are focussed on the development, analysis, and application of deep learning models and methods. I am particularly interested in analysing and developing probabilistic models and inference methods, investigating biologically plausible deep learning, and understanding the stochastic processes involved in the training and optimisation of neural networks and probabilistic models.

  • Algorithms
  • Applications
  • Theory

The optimization of adaptive systems workgroup is concerned with the design and analysis of adaptive information processing systems. We are interested in systems that improve over time through learning, self-adaptation, and evolution. Our systems improve autonomously based on data, in contrast to manual instruction or programming.

Currently wa are working on:

  • fast training and model selection for support vector machines
  • learning in deep networks
  • development of new evolutionary search algorithms and their analysis
  • open source implementation of a large number of machine learning algorithms
  • Algorithms
  • Applications
  • Theory

My research group "Trustworthy Human Language Technologies" focuses on privacy-preserving natural language processing, legal natural language
processing, legal argumentation, and explainable and trustworthy models. In a nutshell, our aim is to design methods that protect people's privacy and are trustworthy.

  • Algorithms
  • Applications
  • Theory

The chair of Artificial Intelligence and Formal Methods has a mission:
Increase the trustworthiness of Artificial Intelligence (AI).

We conduct broad foundational and application-driven research. Our vision of neurosymbolic AI brings together the areas of machine learning and formal methods, in particular, formal verification. We tackle problems that are inspired by autonomous systems and planning problems in robotics.

The following goals are central to our efforts:

  • Increase the dependability of AI in safety-critical environments.
  • Render AI models robust against uncertain knowledge about their environment.
  • Enhance the capabilities of formal verification to handle real-world problems using learning techniques.

We are interested in various aspects of dependability and safety in AI, intelligent decision-making under uncertainty, and safe reinforcement Learning. A key aspect of our research is a thorough understanding of the (epistemic or aleatoric) uncertainty that may occur when AI systems operate in the real world.

  • Algorithms
  • Cognitive modeling

In my group we use computational models and advanced data analysis methods to identify neural mechanisms of cognitive functions. Currently we are interested in the following topics:

  • Computational models of dopamine signalling
  • Reinforcement learning models of animal behaviour
  • Cognitive functions and mechanisms of transient oscillations in the brain
  • Executive functions and memory
  • Developing new analysis methods for large data sets
  • Applying advanced analysis methods, such as machine learning, to Open Neural Data
  • Cognitive modeling

Our research in autonomous robotics is aimed at demonstrating that neural dynamic architectures of embodied cognition can generate object-oriented actions and simple forms of cognition. We organize the work around a scenario in which a partially autonomous robot system interacts with human operators with whom they share a natural environment. The robot system must acquire scene understanding to interpret user commands and autonomously perform actions such as orienting toward objects, retrieving them, possibly manipulating them and handing them over to the human operator. Based on analogies with how nervous systems generate motor behavior and simple forms of cognition, we use attractor dynamics and their instabilities at three levels to generate movement trajectories, to generate goal-directed sequences of behaviors, and to derive task-relevant perceptual representations that support goal-directed behavior.

avatar
Prof. Dr. Laurenz Wiskott
Theory of Neural Systems
Unsupervised Learning, Computational Neuroscience (Vision & Hippocampus)
(+49) 234-32-27997
laurenz.wiskott@ini.rub.de
NB 3/29
  • Algorithms
  • Cognitive modeling
  • Theory

The focus of my interdisciplinary research group lies on principles of self-organization in neural systems, ranging from artificial neural networks to the hippocampus. By bringing together machine learning and computational neuroscience we explore ways of extracting representations from data that are useful for goal-directed learning, such as reinforcement learning.

  • Algorithms
  • Applications
  • Theory

My research interests are in the area of human-centric Artificial Intelligence (AI) and Machine Learning (ML). My work aims to address challenges that arise when AI/ML models interact with human users. For instance, I develop algorithms for making AI/ML models more fair, explainable and robust.

Faculty of Biology

  • Applications

Our research operates at the intersection of Biology, Medicine and Pattern Recognition. In a multidisciplinary team involving
Biologists and Computer Scientists as well as Biochemsists, we work on questions in biomedical research that can be tackled using quantitative analysis of microscopic images. Our philosophy is that such biomedical reseach questions will be answered appropriately by algorithmic modeling, i.e., by translating them into dedicated, problem specific machine learning algorithms.

Faculty of Electrical Engineering

  • Algorithms
  • Applications

Intelligent methods are needed for process supervision and control of technological systems. This is the focus for the institute of Automation and Computer Control. Research is geared to new modeling, analysis and control methods with three focal points:

  • Control theory
  • Modeling and design of hybrid (mixed continuous-discrete) systems, and
  • Process diagnosis and fault-tolerant control.
  • Algorithms
  • Applications

We are interested in the characterization of fundamental limits on information generation and processing for various applications, such as:

  • Interference Management
  • Wireless Sensing: Diagnosis and prediction
  • Robust Beamforming and applied optimization methods
  • UAV communications and signal processing
  • Provable Physical Layer Security
  • Machine Learning for Communication Systems
  • PHY Caching
  • Fog networks and low-latency communication

As part of our integral approach, we complement the theory with the design of methods that approach those limits. The circle comes to a close by experiments validating our results, such as:

  • Universal Software Radio Peripheral (USRP)
  • Raspberry Pi and Arduino

Faculty of Mathematics

  • Algorithms
  • Theory

Our research is about methods and theory for machine learning. Since recently, we have been working on statistical guarantees for deep learning. Our derivations are based on a wide spectrum of concepts from machine learning, statistics, and probability theory.

  • Theory

My research team considers and analyzase machine learning problems from the perspective of complexity theory. We try to determine the information or computational complexity of learning problems, and to design efficient learning algorithms. Furthermore, we investigate combinatorial optimization problems and explore the possibility of designing efficient approximation algorithms. We have a general interest in finding new methods for algorithm design and in inventing new data structures. We are furthermore interested in any results that shed more light on the famous P-NP problem.

Faculty of Mechanical Engineering

avatar
Prof. Dr. Klaus Hackl
Mechanics of Materials
Material Theory, Numerical Methods, Structural Mechanics
(+49) 234-32-26025
klaus.hackl@rub.de
IC 03/711
  • Applications

Modern solid-state mechanics roughly covers the following areas: development of effective models for different materials, development and application of effective numerical methods to solve complex problems, development of accurate models for components and structures, and finally experimental verification of models and calculations, and attempts to determine the parameters of the models used. The Institute of Mechanics of Materials is dedicated to specific questions in all these areas. The focus here is on the modeling and simulation of different mechanical problems, regardless of whether the concrete issue now comes from the field of civil engineering, mechanical engineering, or even from other areas such as biomechanics. The chair conducts fundamental research on the theory and numerics of solid mechanics as well as cooperations with users from the academic and industrial sectors.

  • Applications

Our interdisciplinary research is focused on the design and management of information systems, especially AI-based decision support systems and conversational agents, and their impact on individuals as well organizations. In that context, we establish prescriptive design knowledge for explainability in AI-systems and examine its influence, for instance, on users’ (calibrated) trust or skill formation. Further topics refer to the AI-supported future of work and AI agency.

Faculty of Geosciences & Institute for Geology, Mineralogy and Geophysics

  • Algorithms
  • Applications

This workgroup focusses on identifying and characterizing transient plate tectonic motions on the minutes to decades timescale. For this we analyze mainly Global Navigation Satellite Systems (GNSS/"GPS") data from specially-built tectonic grade permanent GNSS stations. We also consider a variety of in-situ and satellite geodetic data to model plate tectonic accelerations within the interacting Earth systems. We busy ourselves with time-series algorithm development, machine learning modelling, kinematic modelling, and GNSS station deployment activities.

Much of our current research is within the scope of the ERC funded project TectoVision. The end goal of this project is to bring us closer to realizing a global surveillance of plate tectonic accelerations, and therefore a better understanding of how plates move in the time between large earthquakes.

Faculty of Medicine

  • Algorithms
  • Applications

In our lab we apply machine learning (ML) and deep learning in particular to neuroscientific problems. We develop new algorithms to improve brain-computer interfaces and interpret data from non-invasive and invasive neural sources. Our aim is to utilize ML and AI in the clinical setting to raise the quality of life for the severely disabled. 

Linguistic Data Science Lab

  • Applications
  • Cognitive modeling

In our research we combine questions from theoretical and computational linguistics using a combination of methods from theoretical linguistics, experimental linguistics and computer linguistics (Linguistic Data Science). On these pages you will find information on current and most recent projects: questions, approaches and teams.
Additionally, you will find up to date interim results, publications, and announcements of upcoming presentations and publications.

Faculty of Philosophy and Educational Research, Institute for Philosophy II

avatar
Jun.-Prof. Dr. Christian Straßer
Research Group for Non-Monotonic Logic and Formal Argumentation (NMLFA)
non-monotonic logics, defeasible reasoning, argumentation, deontic and adaptive logics, agent-based models
(+49) 0234-32-24721
christian.strasser@ruhr-uni-bochum.de
GA 3/39
  • Theory

Christian Straßer investigates logical aspects of defeasible reasoning. His research concerns theoretic foundations of non-monotonic logics and formal argumentation, as well as applications, including formal models of normative reasoning and agent-based models in the social epistemology.

Interdisciplinary Centre for Advanced Materials Simulation

  • Algorithms
  • Applications

The group works on the development of data-driven and physically-based modeling strategies and their application to analysis and interpretation of materials data. At the moment, one of key research topics is the development of physically-based and data-driven models to identify statistically sound correlations between materials chemistry, thermodynamic, microstructure and mechanical data of single crystal Ni- and Co-based super alloys. In comparison to the existing purely phenomenological modeling methods, such hybrid modeling strategies allow to identify the influence of individual physical effects from the considered contribution on selected material properties.

  • Applications

My group applies algorithms and methods from data sciences and machine learning to materials science problems. Our background is in Computational Materials Science. Specific applications currently include data fusion from simulation and experiment to improve interpretability, the development of interatomic potentials based on neural networks for alloys which are not well described by analytical formulations, and data mining in large defect simulations to improve the understanding of their collective behavior in order to inform coarse-grained models.

Faculty for Philology, German Studies

  • Applications

Our group works on natural language processing applications of language data in digital media. On the theoretical side, we build models for representing variable language online, in particular at the discourse level. On the application side, we develop methods for detecting and analysing negative communication practices in social media, for example hate speech and disinformation, using statistical and neural machine learning.

Medical Proteome Center & Center for Proteindiagnostics (PRODI)

avatar
PD Dr. Martin Eisenacher
Medical Bioinformatics
Bioinformatics for Proteomics, Deep Learning for Specturm Identification
(+49) 234-32-18104
martin.eisenacher@rub.de
PRODI E2.269
  • Applications

On the one hand we analyse data sets with biomedical / clinical research questions using clinical and / or lab data, possibly combined with quantitative high-throughput data from (Prote)Omics technologies. Depending on the research question, we usually search for biomarkers supporting diagnosis, therapy response, survival prediction etc. We also try to learn the group structure from the measured data (e.g. "healthy / diseased") and characterize specificity, sensitivity and ROC curves with respect to the predictability of assignment of newly presenting patients / samples to the learned groups. Thus we have methodically the usual practical problems concerning feature selection, avoidance of overfitting and (intra set or independent set)
validation.

On the other hand we try to characterize with deep learning the "dark matter of Proteomics", i.e. the usual phenomenon, that many recorded mass spectra - although looking  high-quality - cannot be identified with known amino acid sequences.

This website is intended to give an overview of the ever growing machine learning and artificial intelligence research done at the Ruhr-University Bochum (RUB). Since RUB researchers from a broad range of disciplines contribute to both fields, this website acts as an up-to-date register for interested researchers and students.

Universitätsstr. 150, Building NB, Room 3/32
D-44801 Bochum, Germany

Tel: (+49) ...
Fax: (+49) ...