17.12.2020
LMU Munich harnesses AI to drive discovery
‘Give me your data and we’ll find patterns,’ says Thomas Seidl, a computer scientist at LMU Munich. Decoding such patterns reveals secrets hidden in everything from bone fossils to ancient languages. And as academia and industry collect more and more data, there is growing interest in using artificial intelligence (AI) techniques to analyse them…
17.12.2020
Advancements in artificial intelligence (AI) open up new perspectives for science - As a central hub for highly innovative research in Europe, LMU Munich plays a key role in probing both the potential of AI and confronting the challenges it presents…
03.12.2020
The Marie Curie Innovative Training Network entitled “Machine Learning Frontiers in Precision Medicine” brings together leading European research institutes in machine learning and statistical genetics, both from the private and public sector, to train 14 early stage researchers. These scientists will apply machine learning methods to health data. The goal is to reveal new insights into disease mechanisms and therapy outcomes and to exploit the findings for precision medicine, which hopes to offer personalized preventive care and therapy selection for each patient.
26.11.2020
We are looking for talented and highly motivated computer scientists (or people with a related background) interested in the design, development, and analysis of novel machine learning methods. The positions are situated within the Munich Center for Machine Learning (MCML), one of the national competence centers for Machine Learning in Germany.
11.09.2020
for his master thesis ‘Large-scale benchmark study of prediction methods using multi-omics data’ supervised by our PI Prof. Dr. Anne-Laure Boulesteix. In the context of MCML an article has been published in the renowned Journal ‘Briefings in Bioinformatics’ as an extension of his master thesis.
01.06.2020
The PIs of TU Munich published 18 papers at CVF/IEEE Conference on Computer Vision and Pattern Recognition (CVPR) this year, the conference with the currently highest impact among all scientific conferences worldwide.
20.12.2019
We are happy to announce that the MCML upgrade proposal is now accepted by BMBF.
14.11.2019
goes to F. Borutta, S. Schmoll, S. Friedl for their contribution ‘Optimizing the Spatio-Temporal Resource Search Problem with Reinforcement Learning’
10.10.2019
Graph Alignment Networks with Node Matching Scores
E. Faerman, O. Voggenreiter, F. Borutta, T. Emrich, M. Berrendorf, M. Schubert
12.09.2019
Spatial Interpolation with Message Passing Framework
E. Faerman, M. Rogalla, N. Strauß, A. Krüger, B. Blümel, M. Berrendorf, M. Fromm, M.Schubert
12.09.2019
Chain-detection Between Clusters
J. Held, A. Beer, T. Seidl
22.08.2019
Optimizing the Spatio-Temporal Resource Search Problem with Reinforcement Learning
F. Borutta, S. Schmoll, S. Friedl
25.07.2019
A Generator for Subspace Clusters
A. Beer, N. S. Schüler, T. Seidl
25.07.2019
Structural Graph Representations based on Multiscale Local Network Topologies
F. Borutta, J. Busch, E. Faerman, A. Klink, M. Schubert
25.07.2019
Clustering Trend Data Time-Series through Segmentation of FFT-decomposed Signal Constituents
D. Kazempour, A. Beer, O. Schrüfer, T. Seidl
25.07.2019
CODEC - Detecting Linear Correlations in Dense Clusters with Comedian-based PCA
D. Kazempour, M. Hunemörder, A. Beer, and T. Seidl
25.07.2019
From Covariance to Comode in context of Principal Component Analysis
D. Kazempour, L. M. Yan, T. Seidl
11.07.2019
MORe++: k-Means Based Outlier Removal on High-Dimensional Data
A. Beer, J. Lauterbach, T. Seidl
11.07.2019
k-Distance Approximation for Memory-Efficient RkNN Retrieval
M. Berrendorf, F. Borutta, P. Kröger
11.07.2019
A Generic Summary Structure for Arbitrarily Oriented Subspace Clustering in Data Streams
F. Borutta, P. Kröger, T. Hubauer
11.07.2019
On coMADs and Principal Component Analysis
D. Kazempour, M. Hünemörder, T. Seidl
11.07.2019
On Co-medians and Principal Component Analysis
D. Kazempour, T. Seidl
16.05.2019
Graph Ordering and Clustering - A Circular Approach
A. Beer, T. Seidl
16.05.2019
LUCK - Linear Correlation Clustering Using Cluster Algorithms and a kNN based Distance Function
A. Beer, D. Kazempour, L. Stephan, T. Seidl
16.05.2019
Graph Ordering and Clustering - A Circular Approach
D. Kazempour, T. Seidl
16.05.2019
Detecting Global Periodic Correlated Clusters in Event Series based on Parameter Space Transform
D. Kazempour, K. Emmerig, P. Kröger, and T. Seidl
29.03.2019
XD-STOD: Cross-Domain Superresolution for Tiny Object Detection
M. Fromm, M. Berrendorf, E. Faerman, Y. Chen, B. Schüss, M. Schubert
12.03.2019
Human Learning in Data Science
A. Beer, D. Kazempour, M. Baur, T. Seidl
12.03.2019
Data on RAILs: On interactive generation of artificial linear correlated data
D. Kazempour, A. Beer, and T. Seidl
27.01.2019
Smarte Wesen: Hat das mit Intelligenz zu tun? Der Informatiker Thomas Seidl und der Statistiker Bernd Bischl debattieren über Maschinelles Lernen, andere Formen von KI und darüber, warum es wichtig ist zu verstehen, wie Rechner damit zu ihren Ergebnissen kommen.
15.01.2019
DICE: Density-based Interactive Clustering and Exploration
D. Kazempour, M. Kazakov, P. Kröger, T. Seidl.
08.01.2019
Rock - Let the points roam to their clusters themselvese
A. Beer, D. Kazempour, T. Seidl
08.01.2019
A Galaxy of Correlations - Detecting Linear Correlated Clusters through k-Tuples Sampling using Parameter Space Transform
D. Kazempour, L. Krombholz, P. Kröger, T. Seidl
08.01.2019
Insights into a running clockwork: On interactive process-aware clustering
D. Kazempour, T. Seidl
11.12.2018
Chain-detection for DBSCAN
J. Held, A. Beer, T. Seidl