M. Sc. Heinke Hihn

I am a research associate within and Ph.D. student the Learning Systems Group headed by Prof. Dr. Dr. Daniel A. Braun.


    I work on learning and optimization problems in artificial learning systems that have to cope with limited resources, such as time and memory. Mainly i am using methods and algorithms from the areas of

    • Information-theoretic Bounded Rationality
    • Reinforcement Learning
    • Monte Carlo Optimization
    • Ensemble Learning




    • Winter 2018/19

      • Master Project Learning Robots 
      • Lecture Foundations And Concepts of Cognitive Systems Modeling
    • Summer Term 2018

      • Master Project Learning Robots
      • Lecture Learning Systems II
    • Winter Term 2017/18

      • Master Project Learning Robots 
      • Lecture Foundations And Concepts of Cognitive Systems Modeling
      • Lecture Learning Systems I
    • Summer Term 2017

      • Master Project Learning Robots 
      • Lecture Learning Systems II

    Bachelor's and Master's Thesis Topics

    I'm interested in Reinforcement Learning and Machine Learning in general, so i offer Bachelor's and Master's thesis topics in this field. Here's a list of ongoing and completed topics i supervise(d):

    • Learning Robotic Arm Manipulation through Imitation Learning (M.Sc.)
    • Detecting Anomalies in medical Images with Deep Convolutional Neural Networks (M.Sc.)
    • Learning to Grasp Cluttered Objects from RGB-D Data (M.Sc.)
    • Segmentation of Web Content via Deep Convolutional Neural Networks (M.Sc.)
    • Information-theoretic Regularization in Neural Networks (B.Sc.)
    • Object Grasping with Probabilistic Movement Primitives (B. Sc.)
    • Mixture-Of-Experts Learning for Probabilistic Movement Primitives (M.Sc.)

    I am organizing a Colloquium for students writing a thesis or planning to do so are being supervised by me. We meet on every second Wednesday at 2:15 p.m. at the Institute for Neural Information Processing. This is mandatory, so if you think about starting a thesis i recommend visiting at least one session.

    The next colloquium will take place on

    7th of January, 2019


    Here is a (incomplete) list of scientific literature i recommend reading and understanding prior to starting a thesis:

    Reinforcement Learning: An Introduction (Book by Sutton & Barto)

    Deep Learning (Book by Goodfellow et al.)

    Bounded Rationality, Abstraction, and Hierarchical Decision-Making: An information-theoretic Optimality Principle.

    Reinforcement Learning in Robotics

    Trust Region Policy Optimization

    Proximal Policy Optimization Algorithms

    Continuous Control with Deep Reinforcement Learning

    Human Level Control Through Deep Reinforcement Learning


    • Hihn H., Gottwald S., Braun D.A. (2018) Bounded Rational Decision-Making with Adaptive Neural Network Priors. In: Pancioni L., Schwenker F., Trentin E. (eds) Artificial Neural Networks in Pattern Recognition. ANNPR 2018. Lecture Notes in Computer Science, vol 11081. Springer, Cham [link | arxiv]
    • Hihn H., Meudt S., Schwenker F.: Inferring mental overload based on postural behavior and gestures. Proceedings of the 2nd workshop on Emotion Representations and Modelling for Companion Systems. ACM (2016/11/16) [link]
    • Hihn H., Meudt S., Schwenker F.: On Gestures and Postural Behavior as a Modality in Ensemble Methods. IAPR Workshop on Artificial Neural Networks in Pattern Recognition. Springer International Publishing (2016/9/28) [link]