Learning Causal Representations
Dr. Stefan Bauer, KTH Royal Institute of Technology, Stockholm
| Kurzübersicht | |
|---|---|
| Art des Termins |
|
| Wann |
21.06.2022 von 09:00 bis 10:00 |
| Wo | Room no. 0.016 |
| Termin übernehmen |
 vCal iCal
|
Research Talk: Learning Causal Representations
Many questions in everyday life as well as in research are causal in nature: How would the climate change if we lower train prices or will my headache go away if I take an aspirin? Inherently, such questions need to specify the causal variables relevant to the question. A central problem for AI and many application areas is thus the discovery of high-level causal variables from low-level observations like pixel values. While deep neural networks have achieved outstanding success in learning powerful representations for prediction, they fail to explain the effect of interventions. As a way forward to learn causal representations from data, this talk will describe our recent advances of combining interventions and causal structure with deep learning based approaches, as well as our efforts to create real-world benchmarks for the interactive learning paradigm.
Teaching: A Primer on Causal Learning
In many tasks ranging from computer vision to natural language processing we search for the best prediction of some random variable. However, in many situations we are interested in a system's behavior under interventions. For such an analysis, we require the knowledge of the underlying causal structure. This primer is aimed at introducing the fundamental concepts of causal inference as well as connections and synergies with deep learning for causal discovery.
Location: Institute of Computer Science, Friedrich-Hirzebruch-Allee 8, 53115 Bonn, 0.016
