Our research experts

Dr. Jan Hendrik Metzen

Senior Expert in Robust Scalable Perception at the Bosch Center for Artificial Intelligence

“Artificial intelligence can make a key contribution toward solving many of our most urgent problems. But it will only be accepted if we know its limitations, use it responsibly, and are able to communicate how it reaches its decisions.”

Dr. Jan Hendrik Metzen

I am a Senior Expert in Robust Scalable Perception at the Bosch Center for Artificial Intelligence. My research is motivated by the desire to advance the understanding, robustness, and applicability of deep learning-based perception. In particular, I focus on evaluating and increasing the robustness of neural networks. While neural networks excel in classifying data coming from the distribution they have been trained on, they often perform poorly on data with slightly different properties. Addressing this shortcoming is crucial for applying neural network-based perception in safety-critical domains such as automated driving, where they will inevitably be faced with situations not encountered or foreseen during training.

Curriculum vitae

Bosch Center for Artificial Intelligence

2016-present
Senior Expert in Robust Scalable Perception, focusing on increasing the robustness of perception systems based on deep learning and developing automated deep learning techniques

German Research Center for Artificial Intelligence (DFKI)

2013-2015
Team leader of the "Sustained Learning" team in the Robotics Innovation Center, focusing on robot learning, Bayesian optimization and supervised learning

University of Bremen

2014
PhD in Hierarchical Reinforcement Learning on "Learning the Structure of Continuous Markov Decision Processes"

Selected publications

  • Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution

    Elsken et al. (2019)

    Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution
    • Thomas Elsken, Jan Hendrik Metzen, Frank Hutter
    • 7th International Conference on Learning Representations
  • Neural Architecture Search: A Survey

    Elsken et al. (2019)

    Neural Architecture Search: A Survey
    • Thomas Elsken, Jan Hendrik Metzen, Frank Hutter
    • Journal of Machine Learning Research 20 (55), 1-21
  • Defending against Universal Perturbations with Shared Adversarial Training

    Mummadi et al. (2019)

    Defending against Universal Perturbations with Shared Adversarial Training
    • Chaithanya Kumar Mummadi, Thomas Brox, Jan Hendrik Metzen
    • International Conference on Computer Vision 2019
  • Scaling provable adversarial defenses

    Wong et al. (2018)

    Scaling provable adversarial defenses
    • Eric Wong, Frank Schmidt, Jan Hendrik Metzen, J. Zico Kolter
    • Advances in Neural Information Processing Systems 2018
  • Adversarial Examples for Semantic Image Segmentation

    Fischer et al. (2017)

    Adversarial Examples for Semantic Image Segmentation
    • Volker Fischer, Chaitanya Kumar Mummadi, Jan Hendrik Metzen, Thomas Brox
    • 5th International Conference on Learning Representations 2017, Workshop Track
  • On Detecting Adversarial Perturbations

    Metzen et al. (2017)

    On Detecting Adversarial Perturbations
    • Jan Hendrik Metzen, Tim Genewein, Volker Fischer, Bastian Bischoff
    • 5th International Conference on Learning Representations
  • Universal Adversarial Perturbations Against Semantic Image Segmentation

    Metzen et al. (2017)

    Universal Adversarial Perturbations Against Semantic Image Segmentation
    • Jan Hendrik Metzen, Mummadi Chaithanya Kumar, Thomas Brox, Volker Fischer
    • International Conference on Computer Vision 2017, 2755-2764
  • Surgical robotics beyond enhanced dexterity instrumentation: a survey of machine learning techniques and their role in intelligent and autonomous surgical actions

    Kassahun et al. (2016)

    Surgical robotics beyond enhanced dexterity instrumentation: a survey of machine learning techniques and their role in intelligent and autonomous surgical actions
    • Yohannes Kassahun, Bingbin Yu, Abraham Temesgen Tibebu, Danail Stoyanov, Stamatia Giannarou, Jan Hendrik Metzen, Emmanuel Vander Poorten
    • International journal of computer assisted radiology and surgery 11/4 553-568
  • Minimum Regret Search for Single-and Multi-Task Optimization

    Metzen (2016)

    Minimum Regret Search for Single-and Multi-Task Optimization
    • Jan Hendrik Metzen
    • 33rd International Conference of Machine Learning 2016
  • Active contextual policy search

    Fabisch and Metzen (2014)

    Active contextual policy search
    • Alexander Fabisch, Jan Hendrik Metzen
    • The Journal of Machine Learning Research 15 (1) 3371-3399

Interview

Dr. Jan Hendrik Metzen

Dr. Jan Hendrik Metzen

Senior Expert in Robust Scalable Perception at the Bosch Center for Artificial Intelligence

Please tell us what fascinates you most about research.

Research enables me to obtain a more in-depth understanding of complex systems. For me, intelligence and the ability to learn are among the most exciting phenomena and our research in the area of machine learning enables me to address outstanding topics in this thematic field in a very in-depth manner. If applied responsibly, research results in this area (especially in the industrial environment) can also make a key contribution toward improving the quality of life and safety of many people.

Dr. Jan Hendrik Metzen

Dr. Jan Hendrik Metzen

Senior Expert in Robust Scalable Perception at the Bosch Center for Artificial Intelligence

What makes research done at Bosch so special?

Research at the Bosch Center for Artificial Intelligence is distinguished by the high degree of freedoms associated with academic research. Regular publication of research results, intensive exchanges with external scientists, and mutual support of dissertations and doctoral theses enable me to further develop the current state of scientific knowledge together with my partners in the academic community. At the same time, close collaboration with Bosch divisions gives us the possibility to swiftly transfer methods developed by us into applications such as driver assistance systems.

Dr. Jan Hendrik Metzen

Dr. Jan Hendrik Metzen

Senior Expert in Robust Scalable Perception at the Bosch Center for Artificial Intelligence

What research topics are you currently working on at Bosch?

My research involves understanding and improving the robustness of neural networks for perception tasks (e.g. pedestrian detection in the emergency braking assistant). An exact understanding and quantification of robustness are key conditions for the usefulness of a perception system in safety-critical applications such as highly-automated driving. Based on this understanding of current limitations, we are researching methods for improving the robustness of neural networks.

Dr. Jan Hendrik Metzen

Dr. Jan Hendrik Metzen

Senior Expert in Robust Scalable Perception at the Bosch Center for Artificial Intelligence

What are the biggest scientific challenges in your field of research?

As yet, we still do not know how to make neural networks as robust as human perception. Malicious and practically imperceptible modifications (“adversarial attacks”) and harmless distortions such as background noise or blurred images can result in entirely misleading predictions by neural networks. Such incomprehensible errors are very problematic when it comes to the acceptance and approval of perception systems even if the system has, on average, better detection rates than human users. Our research contributes toward increasing the robustness of neural networks.

Dr. Jan Hendrik Metzen

Dr. Jan Hendrik Metzen

Senior Expert in Robust Scalable Perception at the Bosch Center for Artificial Intelligence

How do the results of your research become part of solutions "Invented for life"?

We can only conscionably designate a system as providing technology “Invented for life” where we are certain that it works reliably and safely even under unforeseen conditions. This presents us with major challenges, especially for systems based on machine learning. Our research results contribute toward improving the robustness and understanding of systems based on machine learning. Accordingly, they are key contributions toward reliable and safe systems capable of protecting people from accidents and improving their quality of life.

Dr. Jan Hendrik Metzen

Get in touch with me

Dr. Jan Hendrik Metzen
Senior Expert in Robust Scalable Perception at the Bosch Center for Artificial Intelligence
E-mail

Share this on: