Machine Learning Consulting Unit

Mission Statement

Our primary goal is to provide consulting to applied sciences, for example medicine, psychology, biology and others. We aim to provide solutions, that based on our experience and expertise are most suitable to answer the research question at hand.

The Machine Learning Consulting Unit (MLCU) is part of the Munich Center for Machine Learning (MCML) and offers applied researchers scientific consulting regarding the application and evaluation of machine learning methods. Consulting is free of charge (ca. 8h per project) for members of the MCML and the LMU. Consulting outside the MCML and LMU is also possible, but needs to be negotiated on a case by case basis. We also welcome joint research projects with the goal of publication and other forms of cooperation.

If you are interested in consulting, see contact information below. Experience shows, that it is advisable to register for consulting as early in the project as possible or even at the planning stage.

Typical consulting requests

Typical inquiries include, but are not limited to

• choice of method to answer specific research questions
• advice on implementation
• interpretation of the results
• assessment of variable importance and interpretability of black box methods (interpretable machine learning)
• recommendations regarding the application of specific algorithms (e.g., which (hyper)parameters are important, how to tune them, which tuning strategy, …)
• set up of machine learning experiments that allows fair comparisons, e.g., to compare the predictive performance of different methods

Recent and Current Projects, Cooperations and Publications

Some projects (see also publications list below) that resulted from cooperation with applied sciences in the past include

• Personality prediction from eye-tracking data
• External validation of random survival forests for time-to-event prediction
• Survival prediction based on radiomics and image data
• Classifying neck pain status using scalar and functional biomechanical variables using functional data boosting
• Interpretable machine learning models for classifying low back pain status using functional physiological variables
• Wildlife image classification
• Clinical predictive modeling of post-surgical recovery in individuals with cervical radiculopathy
• Automated classification of atmospheric circulation patterns using Deep Learning
• Classification of rain types
• Clustering of German tourist types
• Prediction of sports injuries in football: Recurrent time-to-event analysis using regularized Cox models

Contact

If you are interested in consulting, please register using our webform.

For other request contact mlcu[at]stat.uni-muenchen.de

For statistical consulting also consider contacting the Statistical Consulting Unit (StaBLab).

Our team

Our team consists of senior statisticians and data scientists with multiple years of experience in methodological and applied research as well as industry.

Name				Position
Prof. Bernd Bischl				Principal Investigator
Dr. Andreas Bender				Coordinator
Dr. Ludwig Bothmann				PostDoc
Dr. David Rügamer				Professor for Data Science
Maximilian Weigert				PhD

Publications

1. Weber, T., Ingrisch, M., Bischl, B., & Rügamer, D. (2023, August 21). Constrained Probabilistic Mask Learning for Task-specific Undersampled MRI Reconstruction. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
   link|pdf
2. Weber, T., Ingrisch, M., Bischl, B., & Rügamer, D. (2023). Unreading Race: Purging Protected Features from Chest X-ray Embeddings. ArXiv:2311.01349.
   link|pdf
3. Liew, B. X. W., Kovacs, F. M., Rügamer, D., & Royuela, A. (2023). Automatic Variable Selection Algorithms in Prognostic Factor Research in Neck Pain. Journal of Clinical Medicine, 12(19).
4. Ott, F., Rügamer, D., Heublein, L., Bischl, B., & Mutschler, C. (2023). Auxiliary Cross-Modal Representation Learning With Triplet Loss Functions for Online Handwriting Recognition. IEEE Access, 11, 94148–94172. https://doi.org/10.1109/ACCESS.2023.3310819
5. Bothmann, L., Wimmer, L., Charrakh, O., Weber, T., Edelhoff, H., Peters, W., Nguyen, H., Benjamin, C., & Menzel, A. (2023). Automated wildlife image classification: An active learning tool for ecological applications. Ecological Informatics, 77(102231).
   link|pdf
6. Rath, K., Rügamer, D., Bischl, B., von Toussaint, U., & Albert, C. (2023). Dependent state space Student-t processes for imputation and data augmentation in plasma diagnostics. Contributions to Plasma Physics.
7. Vogel, M., Aßenmacher, M., Gubler, A., Attin, T., & Schmidlin, P. R. (2023). Cleaning potential of interdental brushes around orthodontic brackets-an in vitro investigation. Swiss Dental Journal, 133(9).
   link|pdf
8. Ziegler, I., Ma, B., Nie, E., Bischl, B., Rügamer, D., Schubert, B., & Dorigatti, E. (2022, October 24). What cleaves? Is proteasomal cleavage prediction reaching a ceiling? NeurIPS 2022 Workshop on Learning Meaningful Representations of Life (LMRL).
   link|pdf
9. Kaiser, P., Rügamer, D., & Kern, C. (2022, October 24). Uncertainty as a key to fair data-driven decision making. NeurIPS 2022 Workshop on Trustworthy and Socially Responsible Machine Learning (TSRML).
   link|pdf
10. Ghada, W., Casellas, E., Herbinger, J., Garcia-Benadí, A., Bothmann, L., Estrella, N., Bech, J., & Menzel, A. (2022). Stratiform and Convective Rain Classification Using Machine Learning Models and Micro Rain Radar. Remote Sensing, 14(18).
    link
11. Rath, K., Rügamer, D., Bischl, B., von Toussaint, U., Rea, C., Maris, A., Granetz, R., & Albert, C. (2022). Data augmentation for disruption prediction via robust surrogate models. Journal of Plasma Physics.
12. Mittermeier, M., Weigert, M., Rügamer, D., Küchenhoff, H., & Ludwig, R. (2022). A Deep Learning Version of Hess & Brezowskys Classification of Großwetterlagen over Europe: Projection of Future Changes in a CMIP6 Large Ensemble. Environmental Research Letters.
13. Liew, B. X. W., Kovacs, F. M., Rügamer, D., & Royuela, A. (2022). Machine learning for prognostic modelling in individuals with non-specific neck pain. European Spine Journal.
14. Liew, B. X. W., Rügamer, D., Duffy, K., Taylor, M., & Jackson, J. (2021). The mechanical energetics of walking across the adult lifespan. PloS One, 16(11), e0259817.
    link
15. Mittermeier, M., Weigert, M., & Rügamer, D. (2021). Identifying the atmospheric drivers of drought and heat using a smoothed deep learning approach. NeurIPS 2021, Tackling Climate Change with Machine Learning.
    link|pdf
16. Weber, T., Ingrisch, M., Fabritius, M., Bischl, B., & Rügamer, D. (2021). Survival-oriented embeddings for improving accessibility to complex data structures. NeurIPS 2021 Workshops, Bridging the Gap: From Machine Learning Research to Clinical Practice.
    link|pdf
17. Weber, T., Ingrisch, M., Bischl, B., & Rügamer, D. (2021). Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation. NeurIPS 2021 Workshops, Deep Generative Models and Downstream Applications.
    link|pdf
18. Liew, B. X. W., Rügamer, D., Zhai, X. J., Morris, S., & Netto, K. (2021). Comparing machine, deep, and transfer learning in predicting joint moments in running. Journal of Biomechanics.
19. Ott, F., Rügamer, D., Heublein, L., Bischl, B., & Mutschler, C. (2021, October 3). Joint Classification and Trajectory Regression of Online Handwriting using a Multi-Task Learning Approach. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
20. Python, A., Bender, A., Blangiardo, M., Illian, J. B., Lin, Y., Liu, B., Lucas, T. C. D., Tan, S., Wen, Y., Svanidze, D., & Yin, J. (2021). A Downscaling Approach to Compare COVID-19 Count Data from Databases Aggregated at Different Spatial Scales. Journal of the Royal Statistical Society: Series A (Statistics in Society). https://doi.org/10.1111/rssa.12738
21. Fabritius, M. P., Seidensticker, M., Rueckel, J., Heinze, C., Pech, M., Paprottka, K. J., Paprottka, P. M., Topalis, J., Bender, A., Ricke, J., Mittermeier, A., & Ingrisch, M. (2021). Bi-Centric Independent Validation of Outcome Prediction after Radioembolization of Primary and Secondary Liver Cancer. Journal of Clinical Medicine, 10(16), 3668. https://doi.org/10.3390/jcm10163668
22. Falla, D., Devecchi, V., Jimenez-Grande, D., Rügamer, D., & Liew, B. (2021). Modern Machine Learning Approaches Applied in Spinal Pain Research. In Journal of Electromyography and Kinesiology.
23. Python, A., Bender, A., Nandi, A. K., Hancock, P. A., Arambepola, R., Brandsch, J., & Lucas, T. C. D. (2021). Predicting non-state terrorism worldwide. Science Advances, 7(31), eabg4778. https://doi.org/10.1126/sciadv.abg4778
24. Liew, B., Lee, H. Y., Rügamer, D., Nunzio, A. M. D., Heneghan, N. R., Falla, D., & Evans, D. W. (2021). A novel metric of reliability in pressure pain threshold measurement. Scientific Reports (Nature).
25. Liew, B. X. W., Peolsson, A., Rügamer, D., Wibault, J., Löfgren, H., Dedering, A., Zsigmond, P., & Falla, D. (2020). Clinical predictive modelling of post-surgical recovery in individuals with cervical radiculopathy – a machine learning approach. Scientific Reports.
    link
26. Schratz, P., Muenchow, J., Iturritxa, E., Cortés, J., Bischl, B., & Brenning, A. (2020). Monitoring forest health using hyperspectral imagery: Does feature selection improve the performance of machine-learning techniques?
    link
27. Bender, A., Python, A., Lindsay, S. W., Golding, N., & Moyes, C. L. (2020). Modelling geospatial distributions of the triatomine vectors of Trypanosoma cruzi in Latin America. PLOS Neglected Tropical Diseases, 14(8), e0008411. https://doi.org/10.1371/journal.pntd.0008411
28. Dorigatti, E., & Schubert, B. (2020). Joint epitope selection and spacer design for string-of-beads vaccines. BioRxiv. https://doi.org/10.1101/2020.04.25.060988
29. Pfister, F. M. J., Um, T. T., Pichler, D. C., Goschenhofer, J., Abedinpour, K., Lang, M., Endo, S., Ceballos-Baumann, A. O., Hirche, S., Bischl, B., & others. (2020). High-Resolution Motor State Detection in parkinson’s Disease Using convolutional neural networks. Scientific Reports, 10(1), 1–11.
    link
30. Stachl, C., Au, Q., Schoedel, R., Gosling, S. D., Harari, G. M., Buschek, D., Völkel, S. T., Schuwerk, T., Oldemeier, M., Ullmann, T., & others. (2020). Predicting personality from patterns of behavior collected with smartphones. Proceedings of the National Academy of Sciences.
    link | pdf
31. Liew, B. X. W., Rügamer, D., Stöcker, A., & De Nunzio, A. M. (2020). Classifying neck pain status using scalar and functional biomechanical variables – development of a method using functional data boosting. Gait & Posture, 75, 146–150.
    link
32. Liew, B., Rügamer, D., De Nunzio, A., & Falla, D. (2020). Interpretable machine learning models for classifying low back pain status using functional physiological variables. European Spine Journal, 29, 1845–1859.
    link
33. Liew, B. X. W., Rügamer, D., Abichandani, D., & De Nunzio, A. M. (2020). Classifying individuals with and without patellofemoral pain syndrome using ground force profiles – Development of a method using functional data boosting. Gait & Posture, 80, 90–95.
    link
34. Dorigatti, E., & Schubert, B. (2020). Graph-theoretical formulation of the generalized epitope-based vaccine design problem. PLOS Computational Biology, 16(10), e1008237. https://doi.org/10.1371/journal.pcbi.1008237
35. Völkel, S. T., Schödel, R., Buschek, D., Stachl, C., Au, Q., Bischl, B., Bühner, M., & Hussmann, H. (2019). Opportunities and challenges of utilizing personality traits for personalization in HCI. Personalized Human-Computer Interaction, 31–65.
    link
36. Pfister, F. M. J., von Schumann, A., Bemetz, J., Thomas, J., Ceballos-Baumann, A., Bischl, B., & Fietzek, U. (2019). Recognition of subjects with early-stage Parkinson from free-living unilateral wrist-sensor data using a hierarchical machine learning model. JOURNAL OF NEURAL TRANSMISSION, 126(5), 663–663.
37. Stachl, C., Au, Q., Schoedel, R., Buschek, D., Völkel, S., Schuwerk, T., Oldemeier, M., Ullmann, T., Hussmann, H., Bischl, B., & Bühner, M. (2019). Behavioral Patterns in Smartphone Usage Predict Big Five Personality Traits. https://doi.org/10.31234/osf.io/ks4vd
38. Schuwerk, T., Kaltefleiter, L. J., Au, J.-Q., Hoesl, A., & Stachl, C. (2019). Enter the Wild: Autistic Traits and Their Relationship to Mentalizing and Social Interaction in Everyday Life. Journal of Autism and Developmental Disorders. https://doi.org/10.1007/s10803-019-04134-6
39. König, G., & Grosse-Wentrup, M. (2019). A Causal Perspective on Challenges for AI in Precision Medicine.
    link
40. Goschenhofer, J., Pfister, F. M. J., Yuksel, K. A., Bischl, B., Fietzek, U., & Thomas, J. (2019). Wearable-based Parkinson’s Disease Severity Monitoring using Deep Learning. Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2019, 400–415.
    link | pdf
41. Fossati, M., Dorigatti, E., & Giuliano, C. (2018). N-ary relation extraction for simultaneous T-Box and A-Box knowledge base augmentation. Semantic Web, 9(4), 413–439. https://doi.org/10.3233/SW-170269
42. Rietzler, M., Geiselhart, F., Thomas, J., & Rukzio, E. (2016). FusionKit: a generic toolkit for skeleton, marker and rigid-body tracking. Proceedings of the 8th ACM SIGCHI Symposium on Engineering Interactive Computing Systems, 73–84.
    link
43. Rueger, S., Goschenhofer, J., Nath, A., Firsching, M., Ennen, A., & Bischl, B. (2022). Deep-Learning-based Aluminum Sorting on Dual Energy X-Ray Transmission Data. Sensor-Based Sorting and Control. https://doi.org/10.2370/9783844085457