Introducing the Scientists

Get an overview of the scientific ML2R team! The scientists introduce themselves with a short profile and reveal topics they are currently working on, which Machine Learning aspects they are particularly interested in and to which of the ML2R research focus areas their work contributes.

Katharina Beckh
Katharina Beckh

Research Focus:

Human-oriented modeling, ML and Complex Knowledge

What problems are you currently working on?

  1. Modeling visual attention of anesthesiologists with focus on effort
  2. Steering active learning models with expert input
  3. Identification of bad medical reporting with text mining tools

What are you particularly interested in?

Interactive Machine Learning, improving the interaction between humans and machine learning algorithms by designing suitable interfaces and models.

David Biesner

Research Focus:

ML and Complex Knowledge

What problems are you currently working on?

  1. Interpretable NLP: Human readable approaches to word embeddings and topic modeling using matrix factorization
  2. Deep-learning based methods for domain-specific NLP, mainly text classification and text generation

What are you particularly interested in?

My main research focus is natural language processing (NLP). I am interested in the power of modern deep-learning architectures for general language understanding and transfer learning, and the possibilities of augmenting these approaches with human knowledge.

Daniel Boiar

Research Focus:

ML and Complex Knowledge

What problems are you currently working on?

  1. Building a knowledge base about multivariate time series algorithms
  2. Outlier detection with Support Vector Machines

What are you particularly interested in?

I am interested in derivation of new and reliable time series algorithms to optimize the analysis of heterogeneous sensor time series in an industrial context.

Kostadin Cvejoski
Kostadin Cvejovski

Awards:

Syngenta 2019 Crop Challenge

Research Focus:

ML and Complex Knowledge

What problems are you currently working on?

  1. Improvement of recommender systems by using the text and time component of user-item interaction
  2. Use of deep neural networks to model queuing systems

What are you particularly interested in?

Development of methods that incorporate temporal and textual information to model how the inspection data of objects (products, companies, …) change over time.

Tobias Deußer

Research Focus:

ML and Complex Knowledge

What problems are you currently working on?

  1. Developing NLP models to understand the relations between text and accompanying tables and create meaningful numerical representations of table cells.
  2. Text generation leveraging the power of deep learning models

What are you particularly interested in?

Finding ways to fuse modern Natural Language Processing models and expert knowledge so that we can minimise the effective resource requirements of said NLP models.

Dr. Tiansi Dong

Awards:

Best Paper Award at ICANN 2019

Research Focus:

Trustworthy ML

What problems are you currently working on?

  1. Surveying recent papers on ‘Vision and Language’
  2. Reproduction of experiments in some of the papers
  3. Region-based knowledge graph reasoning

What are you particularly interested in?

I am interested in the unification of symbolic structures and in deep learning and its applications in Natural Language Understanding, knowledge graph reasoning and Visual-Language interaction.

Raphael Fischer
Raphael Fischer

Research Focus:

Human-oriented modeling, ML and Complex Knowledge

What problems are yoou currently working on?

Application of probabilistic ML to spatio-temporal data, such as image time series, using generative ML to fill gaps in incomplete data sets, such as cloudy satellite image data

What are you particularly interested in?

To investigate how probabilistic ML can contribute to understanding our world while transferring knowledge and perception to other research areas and even to society in general.

Bogdan Georgiev
Dr. Bogdan Georgiev

Awards:

  1. Syngenta 2019 Crop Challenge
  2. Graduate Scholarship, Max Planck Institute for Mathematics, Bonn

Research Focus:

ML and Complex Knowledge, modular ML, human-oriented ML, trustworthy ML, Quantum ML

What problems are you currently working on?

  1. Theory and applications of representation and manifold Learning
  2. Statistical Learning Theory – compression, complexity and generalization bounds
  3. Autoencoding techniques with applications to image and speech data
  4. Quantum Machine Learning – Variational Quantum Circuits

What are you particularly interested in?

The mathematics behind deep learning models and discrete-program inference with applications in training algorithms and generalization performance.

Sven Giesselbach
Sven Giesselbach

Research Focus:

ML and Complex Knowledge

What problems are you currently working on?

  1. Transferring knowledge from “labeled” domains to “unlabeled” domains with our algorithm named Corresponding Projections
  2. Including structured knowledge in text representations such as Word2Vec or BERT

What are you particularly interested in?

I think the assumption that computers can learn to understand natural language simply by consuming as many texts as possible is fundamentally flawed and I would like to explore mechanisms to incorporate external knowledge in natural language understanding.

Felix Gonsior

Research Focus:

Human-oriented ML, trustworthy ML

What problems are you currently working on?

  1. Interpreting optimization problems originating from training Machine Learning models as probabilistic models. This adds the possibility to evaluate and compare many possible alternative solutions.
  2. Inference via sampling on PGMs with quality guarantees for given sample sizes.

What are you particularly interested in?

Understanding the role of uncertainty in ML training and inference and it’s effect on the generalization ability of machine learning models.

Lukas Heppe

Research Focus:

Distributed Learning, High performance computing, Probabilistic graphical models

What problems are you currently working on?

  1. Resource-Constrained Distributed Model aggregation for improving communication efficiency
  2. Modular parameter aggregation for Markov Random Fields
  3. Distributed and parallel inference for Markov Random Fields

What are you particularly interested in?

Development of communication-efficient distributed learning algorithms that enable the dissemination of machine learning methods to a large number of devices, which in turn can jointly benefit from each other.

Lars Patrick Hillebrand

Research Focus:

ML and Complex Knowledge

What problems are you currently working on?

  1. Development of matrix factorization methods for joint learning of word embeddings and extraction of topics and their relations among each other.
  2. Metric learning for automatic evaluation of text summarization systems based on common human criteria.

What are you particulary interested in?

Combining structured knowledge and statistical learning in order to improve text representation learning and knowledge extraction (e.g. topics extraction, text summarization) in the context of Natural Language Processing and Understanding.

Philipp-Jan Honysz

Research Focus:

Human oriented modeling, Industrial application of machine learning

What problems are you currently working on?

  1. Detection of outliers in industrial process data with focus on reduction of rejects and energy demand
  2. Production support through explanation of predicted results

What are you particulary interested in?

Definition of adequate ML-pipelines for the processing of high-volume process data.

Real-time forecasting supported by modern hardware.

Dr. Sebastian Houben
Matthias Jakobs

Research Focus:

Trustworthy ML

What problems are you currently working on?

  1. Providing guarantees in theory and application for explainability methods using Shapley values
  2. Combining explainability models with Bayesian Neural Networks (BNN)

What are you particularly interested in?

Shining a light into the decision-making process of black-box models giving users and experts confidence in the decisions produced by Neural Networks

Birgit Kirsch
Birgit Kirsch

Research Focus:

ML and Complex Knowledge

What problems are you currently working on?

  1. Cold-start knowledge base population by utilizing prior knowledge, e.g. ontologies, domain-specific constraints, …
  2. Noise reduction in distantly supervised datasets for relation extraction via statistical relational learning

What are you particularly interested in?

Joint learning of neural networks and logic based systems

Helena Kotthaus
Dr. Helena Kotthaus
Jens Leveling

Research Focus:

Resource-Constrained Learning

What problems are you currently working on?

  1. Resource-Constrained Learning for Logistics Use-Cases
  2. Industry Transfer of ML2R results – Main focus on Logistics Use-Cases

What are you particularly interested in?

Machine Learning on Internet-of-Things devices: Machine Learning for Classification, Detection and Tracking in Logistics Use-Cases

Industry transfer issues: Getting and creating training data shifting Machine Learning results on an operational level

Mojtaba Masoudinejad

Research Focus:

Resource-Constrained Learning, Industrial application of Machine Learning

What problems are you currently working on?

6D pose estimation of logistics objects in production and warehousing

What are you particularly interested in?

Low cost industrial object detection using computer vision and machine learning

Sascha Mücke

Research Focus:

Resource-Contrained ML, Quantum ML

What problems are you currently working on?

  1. Implementing and continually improving a FPGA-based hardware solver for Ising models
  2. Exploring applications of MAP solvers, specifically for analyzing probabilistic models

What are you particularly interested in?

Probabilistic graphical models; quantum-based optimization and its potential applications to machine learning

Sebastian Müller

Research Focus:

Trustworthy Machine Learning

What problems are you currently working on?

  1. A user-centered quantifying measures for quality assessment of explanations.
  2. Word sense disambiguation using a hybrid approach.

What are you particularly interested in?

Equipping ML Models with a combination of an abstract reasoning mechanism and complex knowledge to obtain an interpretable model that is able to produce situation dependent explanations.

Andreas Pauly

Research Focus:

Resource-Constrained Learning, Theory of Modular Machine Learning

What problems are you currently working on?

  1. Transferring Machine Learning methods from research to industry
  2. Regularization of deep learning methods to reduce the required training resources

What are you particularly interested in?

I am interested in enhancing low-resource Machine Learning methods to enable an inexpensive industry transfer.

Dr. Nico Piatkowski
Dr. Ramses Sanchez
Till Hendrik Schulz

Research Focus:

ML and Complex Knowledge

What problems are you currently working on?

  1. Graph Kernels based on a distance measure using tree edit distances of local tree structures
  2. Computationally feasible graph pattern matching algorithms using constrained homomorphism

What are you particularly interested in?

Learning on graphs, particularly knowledge extraction from single networks or sets of graphs with provable bounds or guarantees

Florian Seiffarth

Research Focus:

ML and Complex Knowledge

What problems are you currently working on?

  1. Enriching abstract closure systems by additional information, such as distances, with the goal of efficient classification, e.g. achieving maximal separations in closure systems based on monotone linkage functions
  2. Neural network layers with weight sharing based on data dependent rules (expert knowledge), applications to graph and node classifications and learning on “complex” data structures

What are you particularly interested in?

Mathematical understanding of Machine Learning with applications to abstract closure systems, e.g. closed frequent item sets, concept lattices etc. and learning on graphs, e.g. graph neural networks based on data dependent rules.

Eike Stadtländer

Research Focus:

ML and Complex Knowledge

What problems are you currently working on?

  1. Learning closure systems, e.g. from transactional databases for application in frequent itemset mining
  2. Convexity conditions in graphs, e.g. for simultaneous clustering

What are you particularly interested in?

Bridging the gap between theory and practical algorithms to improve the interpretability of learning systems.

Hanxiao Tan

Resarch Focus:

Trustworthy Machine Learning

What problems are you currently working on?

Providing model-agnostic explainability methods on 3D point clouds data for better understandable visualisations of 3D neural networks

What are you particularly interested in?

More accurate, efficient and intuitive local/global explainability approaches for 3D deep neural networks

Vanessa Toborek

Research Focus:

Trustworthy ML, Hybrid ML

What problems are you currently working on?

  1. Structured learning algorithms for Natural Language Processing
  2. Use of prior knowledge for the explainability of ML algorithms

What are you particularly interested in?

The question of how to improve a Deep Learning model’s performance and explainability without solely relying on computational power and a posteriori explanations, respectively.

Dr.-Ing. Oliver Urbann

Awards:

Multiple awards in robot soccer, particularly world championship on RoboCup

Resarch Focus:

Resource-Contrained ML

What problems are you currently working on?

Machine Learning compiler

What are you particularly interested in?

Software engineering and Machine Learning in a hardware focus context, e.g. SIMD vectorization, caching, memory limits etc.

Laura von Rueden

Research Focus:

Machine Learning and Complex Knowledge, Trustworthy Machine Learning

What problems are you currently working on?

  1. Informed Machine Learning: A taxonomy and survey of integrating prior knowledge into learning systems
  2. Street-map based validation of semantic segmentation in autonomous driving

What problems are you particularly interested in?

The combination of data-based Machine Learning with knowledge-based modelling (hybrid AI)

Dr. Pascal Welke

Research Focus:

ML and Complex Knowledge

What problems are you currently working on?

  1. Efficient search of frequent subgraphs
  2. Core methods for graphs
  3. Analysis of ML models