Markus Thill
Affiliations. Data Scientist. Karlsruhe/Germany.
Hi there! I’m Markus, a Data Scientist at Atruvia AG. With a background in computer engineering (B.Sc.) and Automation & IT (M.Eng.), I’m passionate about the intersection of machine learning, mathematics, and programming. In my professional role, I delve into data to uncover insights and drive innovation.
I have a particular interest in machine learning approaches, especially in the fields of time series analysis, anomaly detection, Reinforcement Learning (RL) (such as in board games), Deep Learning (DL), and incremental learning procedures. Recently, I received my doctoral certificate from Leiden University for my work titled “Machine Learning and Deep Learning Approaches for Multivariate Time Series Prediction and Anomaly Detection”. This marked a final milestone in my academic journey, and since then, I’ve transitioned into the industry. During my tenure as a research associate at TH Köln, I presented a total of eight peer-reviewed publications at various international research conferences.
Outside of work, I find joy in simple pleasures like flying drones and occasionally solving small mathematical riddles on projecteuler.net. Continuously learning and exploring new concepts in data science and mathematics keeps me motivated and engaged.
news
Jan 15, 2016 | A simple inline announcement with Markdown emoji! |
---|---|
Nov 07, 2015 | A long announcement with details |
Oct 22, 2015 | A simple inline announcement. |
latest posts
May 03, 2024 | Short Notes: Gradient of the Softmax Function for the Cross-Entropy Loss |
---|---|
May 02, 2024 | Obfuscating a Function – How not to write Code |
May 01, 2024 | Short Notes: Eigendecomposition of a Matrix |
selected publications
- ASoCTemporal convolutional autoencoder for unsupervised anomaly detection in time seriesApplied Soft Computing (ASoC), 2021
- ITATAnomaly Detection in Electrocardiogram Readings with Stacked LSTM NetworksIn Proc. 19th Conference Information Technologies - Applications and Theory (ITAT 2019) , 2019Best Paper Award
- PPSNReinforcement learning with n-tuples on the game Connect-4In PPSN’2012: 12th International Conference on Parallel Problem Solving From Nature, Taormina , 2012