Prof. Dr.-Ing.

Bauckhage, Christian

Filters
Reset filters

Settings
Now showing 1 - 6 of 6
  • Publication
    How Does Knowledge Injection Help in Informed Machine Learning?
    ( 2023-08-02)
    Rüden, Laura von
    ;
    Garcke, Jochen
    ;
    Bauckhage, Christian
    Informed machine learning describes the injection of prior knowledge into learning systems. It can help to improve generalization, especially when training data is scarce. However, the field is so application-driven that general analyses about the effect of knowledge injection are rare. This makes it difficult to transfer existing approaches to new applications, or to estimate potential improvements. Therefore, in this paper, we present a framework for quantifying the value of prior knowledge in informed machine learning. Our main contributions are threefold. Firstly, we propose a set of relevant metrics for quantifying the benefits of knowledge injection, comprising in-distribution accuracy, out-of-distribution robustness, and knowledge conformity. We also introduce a metric that combines performance improvement and data reduction. Secondly, we present a theoretical framework that represents prior knowledge in a function space and relates it to data representations and a trained model. This suggests that the distances between knowledge and data influence potential model improvements. Thirdly, we perform a systematic experimental study with controllable toy problems. All in all, this helps to find general answers to the question how knowledge injection helps in informed machine learning.
  • Publication
    Quantum Machine Learning. Eine Analyse zu Kompetenz, Forschung und Anwendung
    (Fraunhofer IAIS, 2020)
    Bauckhage, Christian
    ;
    Brito, Eduardo
    ;
    Daase, Inga
    ;
    Franken, Lukas
    ;
    Georgiev, Bogdan
    ;
    Hecker, Dirk
    ;
    Paschke, Adrian
    ;
    Piatkowski, Nico
    ;
    Soddemann, Thomas
    ;
    Trabold, Daniel
    In unserer Studie »Quantum Machine Learning« geben wir einen Einblick in das Quantencomputing, erklären, welche physikalischen Effekte eine Rolle spielen und wie diese dazu genutzt werden, Verfahren des Maschinellen Lernens zu beschleunigen. Neben den logischen Komponenten werden auch Techniken für die Implementierung der Hardware von Quantencomputern vorgestellt. Die Studie gibt außerdem einen Überblick über die aktuelle Forschungs- und Kompetenzlandschaft und ordnet die Position Deutschlands im internationalen Wettbewerb ein. Zudem stellt die Studie konkrete Anwendungsbereiche und Marktpotenziale für verschiedene Branchen vor. Denn in den kommenden Jahren werden Unternehmen aus unterschiedlichen Branchen vor der Herausforderung stehen, neue Markt- und Geschäftspotenziale mithilfe des Quantencomputings zu erarbeiten, um ihre Wertschöpfung zu steigern. Mit dieser Studie möchten wir Akteuren aus Wirtschaft, Wissenschaft und Gesellschaft Orientierung bieten und die Potenziale aufzeigen, die schon heute sichtbar sind und in Zukunft in Unternehmen Einsatz finden werden.
  • Publication
    Informed Machine Learning - A Taxonomy and Survey of Integrating Knowledge into Learning Systems
    ( 2019-03-29)
    Rüden, Laura von
    ;
    Mayer, Sebastian
    ;
    Beckh, Katharina
    ;
    Georgiev, Bogdan
    ;
    Giesselbach, Sven
    ;
    Heese, Raoul
    ;
    Kirsch, Birgit
    ;
    Pfrommer, Julius
    ;
    Pick, Annika
    ;
    Ramamurthy, Rajkumar
    ;
    Schuecker, Jannis
    ;
    Garcke, Jochen
    ;
    Bauckhage, Christian
    ;
    Walczak, Michal
    Despite its great success, machine learning can have its limits when dealing with insufficient training data. A potential solution is the additional integration of prior knowledge into the training process, which leads to the notion of informed machine learning. In this paper, we present a structured overview of various approaches in this field. First, we provide a definition and propose a concept for informed machine learning, which illustrates its building blocks and distinguishes it from conventional machine learning. Second, we introduce a taxonomy that serves as a classification framework for informed machine learning approaches. It considers the source of knowledge, its representation, and its integration into the machine learning pipeline. Third, we survey related research and describe how different knowledge representations such as algebraic equations, logic rules, or simulation results can be used in learning systems. This evaluation of numerous papers on the basis of our taxonomy uncovers key methods in the field of informed machine learning.
  • Publication
    RatVec: A General Approach for Low-dimensional Distributed Vector Representations via Rational Kernels
    ( 2019)
    Brito, Eduardo
    ;
    Georgiev, Bogdan
    ;
    Domingo-Fernández, Daniel
    ;
    Hoyt, Charles Tapley
    ;
    Bauckhage, Christian
    We present a general framework, RatVec, for learning vector representations of non-numeric entities based on domain-specific similarity functions interpreted as rational kernels. We show competitive performance using k-nearest neighbors in the protein family classification task and in Dutch spelling correction. To promote re-usability and extensibility, we have made our code and pre-trained models available athttps://github.com/ratvec.
  • Publication
    Cognitive Systems and Robotics
    ( 2019)
    Bauckhage, Christian
    ;
    Bauernhansl, Thomas
    ;
    Beyerer, Jürgen
    ;
    Garcke, Jochen
    Cognitive systems are able to monitor and analyze complex processes, which also provides them with the ability to make the right decisions in unplanned or unfamiliar situations. Fraunhofer experts are employing machine learning techniques to harness new cognitive functions for robots and automation solutions. To do this, they are equipping systems with technologies that are inspired by human abilities, or imitate and optimize them. This report describes these technologies, illustrates current example applications, and lays out scenarios for future areas of application.
  • Publication
    Kognitive Systeme und Robotik
    ( 2018)
    Bauckhage, Christian
    ;
    Bauernhansl, Thomas
    ;
    Beyerer, Jürgen
    ;
    Garcke, Jochen
    Kognitive Systeme können komplexe Prozesse überwachen, analysieren und gewinnen daraus auch die Fähigkeit, in ungeplanten oder unbekannten Situationen richtig zu entscheiden. Fraunhofer-Experten setzen Verfahren des maschinellen Lernens ein, um neue kognitive Funktionen für Roboter und Automatisierungslösungen zu nutzen. Dazu statten sie Systeme mit Technologien aus, die von menschlichen Fähigkeiten inspiriert sind bzw. diese imitieren und optimieren. Der Bericht beschreibt diese Technologien, erläutert aktuelle Anwendungsbeispiele und entwirft Szenarien für zukünftige Anwendungsfelder.