Staff profile

Research

I am an interdisciplinary researcher mainly working with methods from machine learning (ML) and artificial intelligence (AI). By building computational models of complex (often cognitive) phenomena I attempt to 1) better understand these phenomena, 2) provide valuable tools for domain experts and end users, and 3) improve the state of the art in ML/AI. Interpretability and robustness is crucial to gain insights and incorporate expert knowledge into the systems.

A focus of my research is on modelling musical structure and perception as a particularly rich and challenging problem. Beyond that, my research includes topics such as the dynamics of communication between agents and the formation of latent/mental representations.

More broadly, I am interested in the development and application of intelligent and autonomous systems, including their social and ethical implications as well as the resulting challenges in arts, legislation and policy making.

Interests

Machine Learning & Artificial Intelligence

• Probabilistic Modelling (Bayesian inference, graphical models, artificial grammars, Monte-Carlo methods, approximate inference)
• Neuro-Symbolic Modelling (end-to-end differentiable parsing algorithms, deep neural networks, structured differentiable models)
• Structure Learning (feature discovery, structure learning in graphical models, parsing algorithms)
• Planning & Decision Making (reinforcement learning, classical planning, Monte-Carlo tree search, heuristic search, active learning)
• Ethical AI (moral reasoning & autonomous systems)
• Medicine (3D medical image analysis (CT/MRI) & semi-automatic segmentation)

Cognitive Modelling

• Music Cognition (perception of harmony & voice leading, hierarchical metrical structure, rhythm, expectation and surprise)
• Communication & Interaction (emergence of symbols in communication, cultural evolution, iterated learning paradigm)

Applications

• Music (music analysis & musical form, new interfaces for musical expression and education)
• Vision (natural scene analysis, modelling semantic/relational structure, human character motion prediction)

Short Bio

Before joining Durham University as an Assistant Professor in Computer Science, I worked as a Postdoc in the Digital and Cognitive Musicology Lab at EPFL, Switzerland (2018–2021). I did my PhD in the Machine Learning and Robotics Lab (now Learning and Intelligent Systems Lab) in Stuttgart/Berlin, Germany (2012–2017) after studying Physics and Philosophy at FU Berlin.

Conference Paper

• Lieck, R., & Rohrmeier, M. (2021, December). Recursive Bayesian Networks: Generalising and Unifying Probabilistic Context-Free Grammars and Dynamic Bayesian Networks. Presented at Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021
• Lieck, R., Wall, L., & Rohrmeier, M. A. (2021, December). Discretisation and Continuity: Simulating the Emergence of Symbols in Communication Games. Presented at Proceedings of the Annual Meeting of the Cognitive Science Society, Vienna, Austria
• Lieck, R., & Rohrmeier, M. (2020, December). Modelling Hierarchical Key Structure With Pitch Scapes. Presented at Proceedings of the 21st International Society for Music Information Retrieval Conference, Montréal, Canada
• Jaccard, T., Lieck, R., & Rohrmeier, M. (2020, December). AutoScale: Automatic and Dynamic Scale Selection for Live Jazz Improvisation. Presented at International Conference on New Interfaces for Musical Expression, Birmingham, United Kingdom
• Landsnes, K., Mehrabyan, L., Wiklund, V., Lieck, R., Moss, F. C., & Rohrmeier, M. (2019, May). A Model Comparison for Chord Prediction on the Annotated Beethoven Corpus. Presented at Proceedings of the 16th Sound \& Music Computing Conference, Málaga, Spain
• Langhabel, J., Lieck, R., Toussaint, M., & Rohrmeier, M. (2017, December). Feature Discovery for Sequential Prediction of Monophonic Music. Presented at Proceedings of the 18th International Society for Music Information Retrieval Conference (ISMIR), Suzhou, China
• Lieck, R., Ngo, V., & Toussaint, M. (2017, December). Exploiting Variance Information in Monte-Carlo Tree Search. Presented at ICAPS Workshop on Heuristics and Search for Domain-independent Planning
• Lieck, R., & Toussaint, M. (2017, December). Active Tree Search. Presented at ICAPS Workshop on Planning, Search, and Optimization
• Kulick, J., Lieck, R., & Toussaint, M. (2016, December). Cross-Entropy as a Criterion for Robust Interactive Learning of Latent Properties. Presented at NIPS Workshop on the Future of Interactive Learning Machines
• Lieck, R., & Toussaint, M. (2015, December). Discovering Temporally Extended Features for Reinforcement Learning in Domains with Delayed Causalities. Presented at European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
• Sharma, G., Ho, K., Saevarsson, S., Ramm, H., Lieck, R., Zachow, S., & Anglin, C. (2012, December). Knee Pose and Geometry Pre- and Post-Total Knee Arthroplasty Using Computed Tomography. Presented at 58th Annual Meeting of the Orthopaedic Research Society (ORS)
• Saevarsson, S., Sharma, G., Montgomery, S., Ho, K., Ramm, H., Lieck, R., Zachow, S., Hutchison, C., Werle, J., & Anglin, C. (2012, December). Kinematic Comparison Between Gender Specific and Traditional Femoral Implants. Presented at 67th Canadian Orthopaedic Association (COA) Annual Meeting
• Saevarsson, S., Sharma, G. B., Montgomery, S. J., Ho, K., Ramm, H., Lieck, R., Zachow, S., & Anglin, C. (2011, December). Kinematic Comparison Between Gender Specific and Traditional Femoral Implants. Presented at Proceedings of the 11th Alberta Biomedical Engineering (BME) Conference (Poster)

Doctoral Thesis

• Lieck, R. (2018). Learning Structured Models for Active Planning: Beyond the Markov Paradigm Towards Adaptable Abstractions. (Thesis). Universität Stuttgart. https://durham-repository.worktribe.com/output/1641954

Journal Article

• Zhang, F. X., Deng, J., Lieck, R., & Shum, H. P. (online). Adaptive Graph Learning from Spatial Information for Surgical Workflow Anticipation. IEEE Transactions on Medical Robotics and Bionics, https://doi.org/10.1109/TMRB.2024.3517137
• Moss, F. C., Lieck, R., & Rohrmeier, M. (2024). Computational modeling of interval distributions in tonal space reveals paradigmatic stylistic changes in Western music history. Humanities and Social Sciences Communications, 11(1), Article 684. https://doi.org/10.1057/s41599-024-03168-1
• Lieck, R., & Rohrmeier, M. (2021). Discretisation and Continuity: The Emergence of Symbols in Communication. Cognition, 215, https://doi.org/10.1016/j.cognition.2021.104787
• Lieck, R., Moss, F. C., & Rohrmeier, M. (2020). The Tonal Diffusion Model. Transactions of the International Society for Music Information Retrieval, 3(1), 153-164. https://doi.org/10.5334/tismir.46
• Wall, L., Lieck, R., Neuwirth, M., & Rohrmeier, M. (2020). The Impact of Voice Leading and Harmony on Musical Expectancy. Scientific Reports, 10(1), 1-8. https://doi.org/10.1038/s41598-020-61645-4
• Dennis, L. A., Tubella, A. A., Chatila, R., Duijf, H., Dyoub, A., Eder, K. I., Horty, J. F., Köhl, M., Lieck, R., & Singh, M. P. (2019). How Do We Build Practical Systems Involving Ethics and Trust?. Dagstuhl Reports, 9(4), 59-86. https://doi.org/10.4230/dagrep.9.4.59
• Lieck, R., & Toussaint, M. (2016). Temporally Extended Features in Model-Based Reinforcement Learning with Partial Observability. Neurocomputing, 192, 49-60. https://doi.org/10.1016/j.neucom.2015.12.107
• Saevarsson, S. K., Sharma, G. B., Ramm, H., Lieck, R., Hutchison, C. R., Werle, J., Matthiasdottir, S., Montgomery, S. J., Romeo, C. I., Zachow, S., & Anglin, C. (2013). Kinematic Differences Between Gender Specific and Traditional Knee Implants. Journal of Arthroplasty, 28(9), 1543-1550. https://doi.org/10.1016/j.arth.2013.01.021
• Sharma, G., Saevarsson, S., Amiri, S., Montgomery, S., Ramm, H., Lichti, D., Lieck, R., Zachow, S., & Anglin, C. (2012). Radiological Method for Measuring Patellofemoral Tracking and Tibiofemoral Kinematics before and after Total Knee Replacement. Bone & Joint Research, 1(10), 263-271. https://doi.org/10.1302/2046-3758.110.2000117
• Ho, K., Saevarsson, S. K., Ramm, H., Lieck, R., Zachow, S., Sharma, G. B., Rex, E., Amiri, S., Wu, B., Leumann, A., & Anglin, C. (2012). Computed Tomography Analysis of Knee Pose and Geometry before and after Total Knee Arthroplasty. Journal of Biomechanics, 45(13), 2215-2221. https://doi.org/10.1016/j.jbiomech.2012.06.004

Report

• Charisi, V., Dennis, L., Fisher, M., Lieck, R., Matthias, A., Slavkovik, M., Sombetzki, J., Winfield, A. F., & Yampolskiy, R. (2017). Towards Moral Autonomous Systems. [No known commissioning body]
• Kulick, J., Lieck, R., & Toussaint, M. (2015). The Advantage of Cross Entropy over Entropy in Iterative Information Gathering. [No known commissioning body]
• Kulick, J., Lieck, R., & Toussaint, M. (2014). Active Learning of Hyperparameters: An Expected Cross Entropy Criterion for Active Model Selection. [No known commissioning body]