I am a research associate and Ph.D. student within 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. Specifically, i investigate such problems in the lifelone learning setting, e.g., meta-learning and continual learning. Sebastian Thrun gives the following definition for lifelone machine learning in the book "Learning to Learn", Chapter 8 "Lifelong Learning Algorithms":

In contrast to most machine learning approaches, which aim at learning a single function in isolation, lifelong learning addresses situations where a learner faces a stream of learning tasks. Such scenarios provide the opportunity for synergetic effects that arise if knowledge is transferred across multiple learning tasks.

 

I'm interested in 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):

Ongoing:

• P. Wolf: Contextual Neurogenesis for Continual Learning Problems (M. Sc.)

Completed:

• C. Graml: Mixture-Of-Experts Learning for Probabilistic Movement Primitives (M.Sc.)
• J. Triep: Learning to Manipulate a Robotic Arm Platform Through Imitation Learning (M. Sc.)
• M. Füßinger: Information-theoretic Regularization in Neural Networks (B.Sc.)
• F. Kneist: Segmentation of Web Content via Deep Convolutional Neural Networks (M.Sc.)
• C. Landgraf: Instance Segmentation in bin-picking Scenarios using Convolutional Neural Networks (M.Sc.)
• N. Mehlhase: Detecting Anomalies in Medical Images with Deep Convolutional Neural Networks (M.Sc.)
• Z. Yeqiang: Object Grasping with Probabilistic Movement Primitives (B. Sc.)
• P. Schwarz: Improving Model-Based Reinforcement Learning with Adaptive Action Priors (M. Sc.)
• L. Wehinger: Deep Generative Replay with Regularized Autoencoder for Long Task Sequences (M.Sc.)
• B. Bernard: Movie Genre Classification based on Transformer Models (M.Sc.)
• J. Eberhardt: Machine Learning Methods for Detecting Fake News (B.Sc.)
• Z. Zhang: Continual Learning in Non-I.I.D. Environments (M.Sc.)
• M. Sirtmatsis: Visualizations for Training Progress in Deep Reinforcement Learning (B.Sc., jointly with A. Bäuerle from the Institute of Media Informatics)
• Y. Berner: Transfer Learning for License Plate Segmentation Deep  Neural Networks (B.Sc.)
• A. Ludwig: Exploring Strategies for Deep Q-Learning (B.Sc.)
• S. Graf: Detecting COVID-19 Infections in Medical X-Ray Images with Deep Convolutional Networks (B. Sc.)
• T. Meuser: Bestimmung der Relevanz von Monitoring-Werten für Machine Learning Systeme (M.Sc.)
• Z. Zhang: Unsupervised skill discovery using variatonal discriminator (M.Sc.)

If you are looking for a thesis in machine learning, feel free to contact me.

2022

• Hihn H., Braun D.A. (2022): Mixture-of-Variational-Experts for Continual learning. In: ICLR Workshop on Agent Learning in Open-Endedness [workshop]
• Hihn H., Braun D.A. (2022): Hierarchically Structured Task-Agnostic Continual Learning. In: accepted for publication in Machine Learning [arxiv preprint]

---

2021

• Thiam P., Hihn H., Braun D.A., Kestler H.A., Schwenker F. (2021): Multi-Modal Pain Intensity Assessment based on Physiological Signals: A Deep Learining Perspective. In: Frontiers in Physiology [link, open access]

---

2020

• Hihn H., Braun D.A. (2020): Hierarchical Expert Networks for Meta-Learning. In: 4th ICML Workshop on Life Long Machine Learning. [workshop]
• Hihn H., Braun D.A. (2020): Specialization in Hierarchical Learning Systems: A Unified Information-theoretic Approach for Supervised, Unsupervised and Reinforcement Learning. In: Neural Processing Letters [link, open access]
• Bellmann P., Hihn H., Braun D.A., Schwenker F (2020.: Binary Classification: Counterbalancing Class Imbalance by Applying Regression Models in Combination with One-Sided Label Shifts, In: 13th International Conference on Agents and Artificial Intelligence ("ICAART") [arxiv preprint]

---

2019

• Hihn H., Gottwald S., Braun D.A. (2019): An Information-theoretic On-Line Learning Principle for Specialization in Hierarchical Decision-Making Systems. In: 58th IEEE Conference on Decision Making and Control, CDC 2019. [arxiv preprint | talk slides]

---

2018

• 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 preprint]

---

2016

• Hihn H., Meudt S., Schwenker F.: Inferring mental overload based on postural behavior and gestures. In: 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. In: IAPR Workshop on Artificial Neural Networks in Pattern Recognition. Springer International Publishing (2016/9/28) [link]

 

See also my Google Scholar Profile.