Ulrich Schaechtle

Researcher and PhD Candidate




Judea Pearl's seminal work on a mathematical framework for causal inference had a wide impact on the AI community. A computational understanding of causality has gained more and more interest since: the community understood that producing rich causal models computationally can be key to creating human-like artificial intelligence. Causal discovery seeks to develop algorithms that learn the structure of causal relations from observation. Diverse problems in domains such as aeronautical engineering, social sciences and bio-medical databases have acted as motivating applications that have gained new insights by applying suitable algorithms to large amounts of non-experimental data, typically collected via the internet or saved in public and private databases.



Statistical Relational Learning (SRL)

Also known as probabilistic logic learning and multirelational data mining, SRL conceptually reunites approaches of machine learning with computational logic and knowledge representation. SRL is concerned with models of domains that build rich structures that can follow diverse kinds of logic, such as description logic, database logic, first-order logic or Horn logic. SRL was successfully applied in biology network mining, activity recognition, decision theory and the identification of adverse drug event. Because SRL makes use of diverse forms of underlying representable knowledge, it aspires to be able to perform reasoning and learning tasks, but also to produce and manipulate rich data, that come with underlying structure or background knowledge. This comes with crucial advantages: parameter sharing and parameter typing allows algorithms for “lifted” computation, that is exploiting and processing the logical structure instead of enumerating every single instance, which can yield critical computational gains. Probabilistic semantics are most often built on probabilistic graphical models.




I am interested in implications and applications of my research in the domains of Biology and Medicine. I am part of COMMODITY12, an international board of experts developing a personal health system to assist in the provision of continuous and personalised health services to diabetic patients. The system consists of ambient and/or body (wearable and portable) devices, which acquire, monitor and communicate physiological parameters and other health-related context of an individual, such as physical activity and vital body signals.
My role in this project is to provide machine learning algorithms, taking into account expert biomedical knowledge and rich datastructures to derive important insights about the individual’s health status given large sets of non-experimental data. Here, I find motivating examples and hard real-world problems to test my theoretical research on.